Journal articles on the topic 'Agent conversationel'
To see the other types of publications on this topic, follow the link: Agent conversationel.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Agent conversationel.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Qin, Zhen (Luther). "Conversational Breakdown Detector for a Motivational Interviewing Conversational Agent." IJournal: Student Journal of the Faculty of Information 9, no. 1 (December 19, 2023): 60–77. http://dx.doi.org/10.33137/ijournal.v9i1.42237.
Abstract:
A conversational breakdown in human-chatbot interaction refers to a disruption or failure in the communicative flow between the human user and the chatbot. To recover a disrupted conversation, the first step is to detect the breakdown. Researchers have proposed methods using supervised learning and semi-supervised learning in dialogue systems to achieve the goal of detecting conversational breakdown. However, few studies have focused on detecting breakdowns in automated therapeutic conversations, especially conversations led by motivational interviewing chatbots. The presence of conversational breakdowns has negative impacts on the human-chatbot interaction, such as frustration, dissatisfaction, or loss of trust. This gap suggests a need to build a robust and efficient conversational breakdown detector that recognizes interruptions during the conversation. Conversational breakdown detection paves the way for further action to recover conversations. In this paper, I develop a novel, unifying framework called “CIMIC” for characterizing the conversational breakdowns of “MIBot,” a motivational interviewing conversational agent for smoking cessation. I collect 200 pieces of conversational data through Prolific and annotate them using the CIMIC framework with a group of four trained annotators. The annotated dataset is then applied as the training set to fine-tune GPT-3 models to build a conversational breakdown detector for the MIBot.
2
Watkinson, Neftali, Fedor Zaitsev, Aniket Shivam, Michael Demirev, Mike Heddes, Tony Givargis, Alexandru Nicolau, and Alexander Veidenbaum. "EdgeAvatar: An Edge Computing System for Building Virtual Beings." Electronics 10, no. 3 (January 20, 2021): 229. http://dx.doi.org/10.3390/electronics10030229.
Abstract:
Dialogue systems, also known as conversational agents, are computing systems that use algorithms for speech and language processing to engage in conversation with humans or other conversation-capable systems. A chatbot is a conversational agent that has, as its primary goal, to maximize the length of the conversation without any specific targeted task. When a chatbot is embellished with an artistic approach that is meant to evoke an emotional response, then it is called a virtual being. On the other hand, conversational agents that interact with the physical world require the use of specialized hardware to sense and process captured information. In this article we describe EdgeAvatar, a system based on Edge Computing principles for the creation of virtual beings. The objective of the EdgeAvatar system is to provide a streamlined and modular framework for virtual being applications that are to be deployed in public settings. We also present two implementations that use EdgeAvatar and are inspired by historical figures to interact with visitors of the Venice Biennale 2019. EdgeAvatar can adapt to fit different approaches for AI powered conversations.
3
Belainine, Billal, Fatiha Sadat, and Hakim Lounis. "Modelling a Conversational Agent with Complex Emotional Intelligence." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 10 (April 3, 2020): 13710–11. http://dx.doi.org/10.1609/aaai.v34i10.7127.
Abstract:
Chatbots or conversational agents have enjoyed great popularity in recent years. They surprisingly perform sensitive tasks in modern societies. However, despite the fact that they offer help, support, and fellowship, there is a task that is not yet mastered: dealing with complex emotions and simulating human sensations. This research aims to design an architecture for an emotional conversation agent for long-text conversations (multi-turns). This agent is intended to work in areas where the analysis of users feelings plays a leading role. This work refers to natural language understanding and response generation.
4
Pilato, Giovanni, Agnese Augello, and Salvatore Gaglio. "A Modular System Oriented to the Design of Versatile Knowledge Bases for Chatbots." ISRN Artificial Intelligence 2012 (March 5, 2012): 1–10. http://dx.doi.org/10.5402/2012/363840.
Abstract:
The paper illustrates a system that implements a framework, which is oriented to the development of a modular knowledge base for a conversational agent. This solution improves the flexibility of intelligent conversational agents in managing conversations. The modularity of the system grants a concurrent and synergic use of different knowledge representation techniques. According to this choice, it is possible to use the most adequate methodology for managing a conversation for a specific domain, taking into account particular features of the dialogue or the user behavior. We illustrate the implementation of a proof-of-concept prototype: a set of modules exploiting different knowledge representation methodologies and capable of managing different conversation features has been developed. Each module is automatically triggered through a component, named corpus callosum, that selects in real time the most adequate chatbot knowledge module to activate.
5
Zhong, Peixiang, Yong Liu, Hao Wang, and Chunyan Miao. "Keyword-Guided Neural Conversational Model." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 16 (May 18, 2021): 14568–76. http://dx.doi.org/10.1609/aaai.v35i16.17712.
Abstract:
We study the problem of imposing conversational goals/keywords on open-domain conversational agents, where the agent is required to lead the conversation to a target keyword smoothly and fast. Solving this problem enables the application of conversational agents in many real-world scenarios, e.g., recommendation and psychotherapy. The dominant paradigm for tackling this problem is to 1) train a next-turn keyword classifier, and 2) train a keyword-augmented response retrieval model. However, existing approaches in this paradigm have two limitations: 1) the training and evaluation datasets for next-turn keyword classification are directly extracted from conversations without human annotations, thus, they are noisy and have low correlation with human judgements, and 2) during keyword transition, the agents solely rely on the similarities between word embeddings to move closer to the target keyword, which may not reflect how humans converse. In this paper, we assume that human conversations are grounded on commonsense and propose a keyword-guided neural conversational model that can leverage external commonsense knowledge graphs (CKG) for both keyword transition and response retrieval. Automatic evaluations suggest that commonsense improves the performance of both next-turn keyword prediction and keyword-augmented response retrieval. In addition, both self-play and human evaluations show that our model produces responses with smoother keyword transition and reaches the target keyword faster than competitive baselines.
6
Goh, Ong Sing, Chun Che Fung, Kok Wai Wong, and Arnold Depickere. "Embodied Conversational Agents for H5N1 Pandemic Crisis." Journal of Advanced Computational Intelligence and Intelligent Informatics 11, no. 3 (March 20, 2007): 282–88. http://dx.doi.org/10.20965/jaciii.2007.p0282.
Abstract:
This paper presents a novel framework for modeling embodied conversational agent for crisis communication focusing on the H5N1 pandemic crisis. Our system aims to cope with the most challenging issue on the maintenance of an engaging while convincing conversation. What primarily distinguishes our system from other conversational agent systems is that the human-computer conversation takes place within the context of H5N1 pandemic crisis. A Crisis Communication Network, called CCNet, is established based on a novel algorithm incorporating natural language query and embodied conversation agent simultaneously. Another significant contribution of our work is the development of a Automated Knowledge Extraction Agent (AKEA) to capitalize on the tremendous amount of data that is now available online to support our experiments. What makes our system differs from typical conversational agents is the attempt to move away from strictly task-oriented dialogue.
7
Lin, Phoebe, Jessica Van Brummelen, Galit Lukin, Randi Williams, and Cynthia Breazeal. "Zhorai: Designing a Conversational Agent for Children to Explore Machine Learning Concepts." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 09 (April 3, 2020): 13381–88. http://dx.doi.org/10.1609/aaai.v34i09.7061.
Abstract:
Understanding how machines learn is critical for children to develop useful mental models for exploring artificial intelligence (AI) and smart devices that they now frequently interact with. Although children are very familiar with having conversations with conversational agents like Siri and Alexa, children often have limited knowledge about AI and machine learning. We leverage their existing familiarity and present Zhorai, a conversational platform and curriculum designed to help young children understand how machines learn. Children ages eight to eleven train an agent through conversation and understand how the knowledge is represented using visualizations. This paper describes how we designed the curriculum and evaluated its effectiveness with 14 children in small groups. We found that the conversational aspect of the platform increased engagement during learning and the novel visualizations helped make machine knowledge understandable. As a result, we make recommendations for future iterations of Zhorai and approaches for teaching AI to children.
8
Dhoolia, Pankaj, Vineet Kumar, Danish Contractor, and Sachindra Joshi. "Bootstrapping Dialog Models from Human to Human Conversation Logs." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 18 (May 18, 2021): 16024–25. http://dx.doi.org/10.1609/aaai.v35i18.18000.
Abstract:
State-of-the-art commercial dialog platforms provide powerful tools to build a conversational agent. These platforms provide complete control to the dialog designer to model user-agent interactions. However, a dialog designer needs to rely on domain experts to manually build the dialog model -- by creating dialog flow nodes and modeling user intents. This process is laborious, time consuming and expensive and does not allow the designer to exploit human to human conversation logs effectively. In this work, we present a research prototype that can ingest human-to-human conversation logs between an end-user and an agent, and suggest user-intents and agent-responses, given a conversation context. We utilize human to human conversation logs to build two emulators: user and agent. An agent emulator models an agent response given the conversation context so far, and a user emulator outputs possible user responses. Our system is able to recommend conversational intents as well as conversation flow using emulators based on real-world data, thus making the process of designing a bot more efficient. To the best our knowledge this is the first system that enables data-driven dialog model creation by emulating users and agents.
9
Raj, Kanak, Kaushik Roy, Vamshi Bonagiri, Priyanshul Govil, Krishnaprasad Thirunarayan, Raxit Goswami, and Manas Gaur. "K-PERM: Personalized Response Generation Using Dynamic Knowledge Retrieval and Persona-Adaptive Queries." Proceedings of the AAAI Symposium Series 3, no. 1 (May 20, 2024): 219–26. http://dx.doi.org/10.1609/aaaiss.v3i1.31203.
Abstract:
Personalizing conversational agents can enhance the quality of conversations and increase user engagement. However, they often lack external knowledge to appropriately tend to a user’s persona. This is crucial for practical applications like mental health support, nutrition planning, culturally sensitive conversations, or reducing toxic behavior in conversational agents. To enhance the relevance and comprehensiveness of personalized responses, we propose using a two-step approach that involves (1) selectively integrating user personas and (2) contextualizing the response by supplementing information from a background knowledge source. We develop K-PERM (Knowledge-guided PErsonalization with Reward Modulation), a dynamic conversational agent that combines these elements. K-PERM achieves state-of-the- art performance on the popular FoCus dataset, containing real-world personalized conversations concerning global landmarks.We show that using responses from K-PERM can improve performance in state-of-the-art LLMs (GPT 3.5) by 10.5%, highlighting the impact of K-PERM for personalizing chatbots.
10
Wu, Zeqiu, Ryu Parish, Hao Cheng, Sewon Min, Prithviraj Ammanabrolu, Mari Ostendorf, and Hannaneh Hajishirzi. "InSCIt: Information-Seeking Conversations with Mixed-Initiative Interactions." Transactions of the Association for Computational Linguistics 11 (May 18, 2023): 453–68. http://dx.doi.org/10.1162/tacl_a_00559.
Abstract:
Abstract In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types according to the available knowledge sources. However, most current studies either fail to or artificially incorporate such agent-side initiative. This work presents InSCIt, a dataset for Information-Seeking Conversations with mixed-initiative Interactions. It contains 4.7K user-agent turns from 805 human-human conversations where the agent searches over Wikipedia and either directly answers, asks for clarification, or provides relevant information to address user queries. The data supports two subtasks, evidence passage identification and response generation, as well as a human evaluation protocol to assess model performance. We report results of two systems based on state-of-the-art models of conversational knowledge identification and open-domain question answering. Both systems significantly underperform humans, suggesting ample room for improvement in future studies.1
11
Huang, Ting-Hao, Walter Lasecki, Amos Azaria, and Jeffrey Bigham. ""Is There Anything Else I Can Help You With?" Challenges in Deploying an On-Demand Crowd-Powered Conversational Agent." Proceedings of the AAAI Conference on Human Computation and Crowdsourcing 4 (September 21, 2016): 79–88. http://dx.doi.org/10.1609/hcomp.v4i1.13292.
Abstract:
Intelligent conversational assistants, such as Apple's Siri, Microsoft's Cortana, and Amazon's Echo, have quickly become a part of our digital life. However, these assistants have major limitations, which prevents users from conversing with them as they would with human dialog partners. This limits our ability to observe how users really want to interact with the underlying system. To address this problem, we developed a crowd-powered conversational assistant, Chorus, and deployed it to see how users and workers would interact together when mediated by the system. Chorus sophisticatedly converses with end users over time by recruiting workers on demand, which in turn decide what might be the best response for each user sentence. Up to the first month of our deployment, 59 users have held conversations with Chorus during 320 conversational sessions. In this paper, we present an account of Chorus' deployment, with a focus on four challenges: (i) identifying when conversations are over, (ii) malicious users and workers, (iii) on-demand recruiting, and (iv) settings in which consensus is not enough. Our observations could assist the deployment of crowd-powered conversation systems and crowd-powered systems in general.
12
Muhammad Bilal Ahmad Jamil and Duryab Shahzadi. "A systematic review A Conversational interface agent for the export business acceleration." Lahore Garrison University Research Journal of Computer Science and Information Technology 7, no. 02 (August 21, 2023): 37–49. http://dx.doi.org/10.54692/lgurjcsit.2023.0702430.
Abstract:
Conversational agents, which understand, respond to, and learn from each interaction using Automatic Speech Recognition (ASR), Natural Language Processing (NLP), Advanced Dialog Management, and Machine Learning (ML), have become more common in recent years. Conversational agents, also referred to as chatbots, are used to have real-time conversations with individuals. As a result, conversational agents are now being used in a variety of sectors, including those in education, healthcare, marketing, customer assistance, and entertainment. Conversational agents, which are frequently used as chatbots and virtual or AI helpers, show how computational linguistics is used in everyday life. It can be challenging to pinpoint the variables that affect the use of conversational agents for business acceleration and to defend their utility in order to enhance export company. This paper provides a summary of the evolution of conversational agents from a straightforward model to a sophisticated intelligent system, as well as how they are applied in various practical contexts. This study contributes to the body of literature on information systems by contrasting the different conversational agent types based on the export business acceleration interface. This paper also identifies the challenges conversational applications experience today and makes recommendations for further research.
13
Li, Mengyao, Isabel M. Erickson, Ernest V. Cross, and John D. Lee. "Estimating Trust in Conversational Agent with Lexical and Acoustic Features." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 66, no. 1 (September 2022): 544–48. http://dx.doi.org/10.1177/1071181322661147.
Abstract:
As NASA moves to long-duration space exploration operations, there is an increasing need for human-agent cooperation that requires real-time trust estimation by virtual agents. Our objective was to estimate trust using conversational data, including lexical and acoustic features, with machine learning. A 2 (reliability) × 2 (cycles) × 3 (events) within-subject study was designed to provoke various levels of trust. Participants had trust-related conversations with a conversational agent at the end of each event. To estimate trust, subjective trust ratings were predicted using machine learning models trained on three types of conversational features (i.e., lexical, acoustic, and combined). Results showed that a random forest model, trained on the combined lexical and acoustic features, best predicts trust in the conversational agent (R2adj = 0.67). Comparing models, we showed that trust is not only reflected in lexical cues but also acoustic cues. These results show the possibility of using conversational data to measure trust unobtrusively and dynamically.
14
Chuang, Hsiu-Min, and Ding-Wei Cheng. "Conversational AI over Military Scenarios Using Intent Detection and Response Generation." Applied Sciences 12, no. 5 (February 27, 2022): 2494. http://dx.doi.org/10.3390/app12052494.
Abstract:
With the rise of artificial intelligence, conversational agents (CA) have found use in various applications in the commerce and service industries. In recent years, many conversational datasets have becomes publicly available, most relating to open-domain social conversations. However, it is difficult to obtain domain-specific or language-specific conversational datasets. This work focused on developing conversational systems based on the Chinese corpus over military scenarios. The soldier will need information regarding their surroundings and orders to carry out their mission in an unfamiliar environment. Additionally, using a conversational military agent will help soldiers obtain immediate and relevant responses while reducing labor and cost requirements when performing repetitive tasks. This paper proposes a system architecture for conversational military agents based on natural language understanding (NLU) and natural language generation (NLG). The NLU phase comprises two tasks: intent detection and slot filling. Detecting intent and filling slots involves predicting the user’s intent and extracting related entities. The goal of the NLG phase, in contrast, is to provide answers or ask questions to clarify the user’s needs. In this study, the military training task was when soldiers sought information via a conversational agent during the mission. In summary, we provide a practical approach to enabling conversational agents over military scenarios. Additionally, the proposed conversational system can be trained by other datasets for future application domains.
15
Kum, Junyeong, and Myungho Lee. "Can Gestural Filler Reduce User-Perceived Latency in Conversation with Digital Humans?" Applied Sciences 12, no. 21 (October 29, 2022): 10972. http://dx.doi.org/10.3390/app122110972.
Abstract:
The demand for a conversational system with digital humans has increased with the development of artificial intelligence. Latency can occur in such conversational systems because of natural language processing and network issues, which can deteriorate the user’s performance and the availability of the systems. There have been attempts to mitigate user-perceived latency by using conversational fillers in human–agent interaction and human–robot interaction. However, non-verbal cues, such as gestures, have received less attention in such attempts, despite their essential roles in communication. Therefore, we designed gestural fillers for the digital humans. This study examined the effects of whether the conversation type and gesture filler matched or not. We also compared the effects of the gestural fillers with conversational fillers. The results showed that the gestural fillers mitigate user-perceived latency and affect the willingness, impression, competence, and discomfort in conversations with digital humans.
16
Young Oh, Eun, Donggil Song, and Hyeonmi Hong. "Interactive Computing Technology in Anti-Bullying Education: The Effects of Conversation-Bot’s Role on K-12 Students’ Attitude Change Toward Bullying Problems." Journal of Educational Computing Research 58, no. 1 (April 10, 2019): 200–219. http://dx.doi.org/10.1177/0735633119839177.
Abstract:
The aim of this study was to examine the effects of an anti-bullying activity that utilizes conversational virtual agents (called conversation-bots or chatbots) on students’ attitudes toward bullying problems. An experimental pre- or posttest design with a three-group setting was used. Eighty-nine fifth-grade students were assigned to one of three groups: Conversation with a virtual agent of (a) bully’s role, (b) victim’s role, and (c) teacher’s role. All agents are conversation-bots designed to support learner–computer interactions. The bully agent defends the notion that bullying behaviors are acceptable whereas the victim agent argues that bullying behavior cannot be tolerated. The teacher agent teaches students the types of bullying and its negative aspects. The participants completed an anti-bullying attitude test at pre- and posttest, which included students’ anti-bully, intention, pro-victim, behavior, and self-efficacy factors. The results show that students’ attitudes toward bullying problems changed to more positive responses after the implementation that used the conversation-bot. In addition, the results revealed that the agent’s role had an impact on the students’ attitudes toward the anti-bully factor. Implications and future research regarding the use of conversation-bots in education are discussed.
17
Rivière, Jérémy, Carole Adam, and Sylvie Pesty. "Langage de conversation multimodal pour agent conversationnel animé." Techniques et sciences informatiques 31, no. 4 (April 30, 2012): 455–76. http://dx.doi.org/10.3166/tsi.31.455-476.
18
Ren, Pengjie, Zhumin Chen, Zhaochun Ren, Evangelos Kanoulas, Christof Monz, and Maarten De Rijke. "Conversations with Search Engines: SERP-based Conversational Response Generation." ACM Transactions on Information Systems 39, no. 4 (October 31, 2021): 1–29. http://dx.doi.org/10.1145/3432726.
Abstract:
In this article, we address the problem of answering complex information needs by conducting conversations with search engines , in the sense that users can express their queries in natural language and directly receive the information they need from a short system response in a conversational manner. Recently, there have been some attempts towards a similar goal, e.g., studies on Conversational Agent s (CAs) and Conversational Search (CS). However, they either do not address complex information needs in search scenarios or they are limited to the development of conceptual frameworks and/or laboratory-based user studies. We pursue two goals in this article: (1) the creation of a suitable dataset, the Search as a Conversation (SaaC) dataset, for the development of pipelines for conversations with search engines, and (2) the development of a state-of-the-art pipeline for conversations with search engines, Conversations with Search Engines (CaSE), using this dataset. SaaC is built based on a multi-turn conversational search dataset, where we further employ workers from a crowdsourcing platform to summarize each relevant passage into a short, conversational response. CaSE enhances the state-of-the-art by introducing a supporting token identification module and a prior-aware pointer generator, which enables us to generate more accurate responses. We carry out experiments to show that CaSE is able to outperform strong baselines. We also conduct extensive analyses on the SaaC dataset to show where there is room for further improvement beyond CaSE. Finally, we release the SaaC dataset and the code for CaSE and all models used for comparison to facilitate future research on this topic.
19
da Silva Fernandes, Ulisses, Glívia Angélica Rodrigues Barbosa, Bruno Azevedo Chagas, Gabriel Diniz Junqueira Barbosa, Simone Diniz Junqueira Barbosa, and Raquel Oliveira Prates. "Lessons Learned from Modeling the Interaction with Conversational Agents." Interaction Design and Architecture(s), no. 55 (February 1, 2023): 139–73. http://dx.doi.org/10.55612/s-5002-055-007.
Abstract:
Intelligent conversational agents have become widespread. Inspired by conversations in natural language, they present different degrees of intelligence and autonomy, bringing challenges for Human-Computer Interaction (HCI). One such challenge concerns design languages for modeling user-agent interaction. We focus here on MoLIC, a design-phase dialogue model based on Semiotic Engineering theory devised to represent user-system interactions as conversations. We performed two case studies with MoLIC interaction diagrams representing two conversational agents – the ANA chatbot and Samsung Bixby. We examined how the interactive aspects of these agents could be expressed in MoLIC. Although it was possible to express the general interaction, our results showed limitations related to the language expressiveness or its inadequacy to represent these systems. We identified limitations in the applicability of MoLIC in modeling and pondered on how to extend or adapt it; directing the HCI community to issues and initiatives that can help design and model these technologies.
20
Oktarini, Kadek Ratih Dwi. "Are You Flirting, Objectifying or What? a Conversation Analysis of “you’re very sexy” Conversational Turn." SOSHUM : Jurnal Sosial dan Humaniora 10, no. 3 (November 28, 2020): 294–308. http://dx.doi.org/10.31940/soshum.v10i3.1972.
Abstract:
Intent identification is one of the most critical components in conversational agent design. Conversational agent “is any dialogue system that not only conducts natural language processing but also responds automatically using human language.” (Conversational Agent, 2019). The crux of designing human-like conversational agent is to mimic how human understands another human and then responds “naturally”. The current study attempts to answer the fundamental question: how to model human processes of understanding another human? In order to answer that question, it starts from exploring some basic concepts relevant to intent identification from Conversation Analysis (CA). CA is a mature field that studies authentic human interaction. The basic concepts from CA are then synthesised into a model that potentially fit to existing framework and paradigm in conversational agent design, i.e. Natural Conversation Framework (NCF) and Intent-Entity-Context-Response (IECR) paradigm. Instead of using a made-up sentence, the model is then tested to an authentic conversational turn seksi sekali dirimu ‘you’re very sexy’. The test shows that the model is able to detect several possible intents contain in this authentic conversational turn. The model is also able to handle Conversational Indonesian and multi-modality. Considering the versatility of Conversation Analysis, in all likelihood the model will be able to handle any language and all kinds of modalities. Future study can be done to analyse more Conversational Indonesian data (to develop library of intent for Conversational Indonesian Language), as well as conversational data from different languages and conversational data containing diverse modalities.
21
Omarov, Batyrkhan, Sergazy Narynov, and Zhandos Zhumanov. "Development of Chatbot-Psychologist: Dataset, Architecture, Design and Chatbot in Use." Вестник КазАТК 123, no. 4 (November 2, 2022): 463–71. http://dx.doi.org/10.52167/1609-1817-2022-123-4-463-471.
Abstract:
Virtual assistants are software applications that allow users to have conversations with the software in the same way as they would in real life. Creating functional conversational agents have been the most challenging aspect of working with AI ever since the field was first introduced. Virtual conversational agents' primary responsibility is to properly interpret natural communication and reply in an acceptable manner, in spite of the fact that they may do a range of activities. In the past, AI agents were created either via the use of handwritten rules and commands or by straightforward statistical approaches. End-to-end Automation has mostly supplanted these models because of its superior potential for learning new skills. The encoder-decoder deep learning approach is currently the method that has the greatest amount of interest for simulating conversations. The domain of linguistic understanding served as a source of motivation for the development of this concept. In this article, we present an overview o the findings from our study into the development of an immersive digital conversational agent that might potentially provide sufferers psychological aid. We used Rasa NLU approach, which is based on NLP practices, in order to construct and train the chatbot. The findings of the study indicated that providing appropriate replies to patients' questions and concerns during conversations had a prediction accuracy about 75 percent.
22
HEYLEN, DIRK. "HEAD GESTURES, GAZE AND THE PRINCIPLES OF CONVERSATIONAL STRUCTURE." International Journal of Humanoid Robotics 03, no. 03 (September 2006): 241–67. http://dx.doi.org/10.1142/s0219843606000746.
Abstract:
Much of the work on embodied conversational agents is concerned with building computational models of nonverbal behaviors that can generate the right behavior in the appropriate context. In this paper, we discuss, from a linguistic and a conversation theoretic point of view, how nonverbal behaviors in conversations work. We look particularly at gaze and head movements. These play a variety of functions in face-to-face interactions. We show how these functions are structured by general principles governing cooperative actions and symbolic communication.
23
Battaglino, Cristina, and Timothy Bickmore. "Increasing the Engagement of Conversational Agents through Co-Constructed Storytelling." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 11, no. 4 (June 24, 2021): 9–15. http://dx.doi.org/10.1609/aiide.v11i4.12832.
Abstract:
Storytelling can be used by conversational agents in a wide variety of domains to maintain user engagement, both within a single interaction and over dozens or hun- dreds of interactions over time. The majority of agents designed with this ability to date deliver their stories as monologues without user input. However, people rarely tell stories in conversations this way, and instead rely on listener contributions to guide the storytelling process. Corpus-based studies of human-human conversational storytelling have demonstrated greater engagement, in the form of longer stories, when listeners co-construct stories this way. We describe a research framework for the generation and evaluation of co-constructed social stories in the context of task-based conversations, and a study on the effects of degree of user-agent story co-construction on user engagement. We find that users are more en- gaged with storytelling agents that allow them to co- construct stories in a contentful manner by asking ques- tions, compared to co-construction through acknowl- edgments only.
24
Avula, Sandeep, Bogeum Choi, and Jaime Arguello. "The Effects of System Initiative during Conversational Collaborative Search." Proceedings of the ACM on Human-Computer Interaction 6, CSCW1 (March 30, 2022): 1–30. http://dx.doi.org/10.1145/3512913.
Abstract:
Our research in this paper lies at the intersection of collaborative and conversational search. We report on a Wizard of Oz lab study in which 27 pairs of participants collaborated on search tasks over the Slack messaging platform. To complete tasks, pairs of collaborators interacted with a so-called searchbot with conversational capabilities. The role of the searchbot was played by a reference librarian. It is widely accepted that conversational search systems should be able to engage in mixed-initiative interaction ---take and relinquish control of a multi-agent conversation as appropriate. Research in discourse analysis differentiates between dialog- and task-level initiative. Taking dialog-level initiative involves leading a conversation for the sole purpose of establishing mutual belief between agents. Conversely, taking task-level initiative involves leading a conversation with the intent to influence the goals of the other agent(s). Participants in our study experienced three searchbot conditions, which varied based on the level of initiative the human searchbot was able to take: (1) no initiative, (2) only dialog-level initiative, and (3) both dialog- and task-level initiative. We investigate the effects of the searchbot condition on six different types of outcomes: (RQ1) perceptions of the searchbot's utility, (RQ2) perceptions of workload, (RQ3) perceptions of the collaboration, (RQ4) patterns of communication and collaboration, and perceived (RQ5) benefits and (RQ6) challenges from engaging with the searchbot.
25
Mathewson, Kory, and Piotr Mirowski. "Improvised Theatre Alongside Artificial Intelligences." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 13, no. 1 (June 25, 2021): 66–72. http://dx.doi.org/10.1609/aiide.v13i1.12926.
Abstract:
This study presents the first report of Artificial Improvisation, or improvisational theatre performed live, on-stage, alongside an artificial intelligence-based improvisational performer. The Artificial Improvisor is a form of artificial conversational agent, or chatbot, focused on open domain dialogue and collaborative narrative generation. Using state-of-the-art machine learning techniques spanning from natural language processing and speech recognition to reinforcement and deep learning, these chatbots have become more lifelike and harder to discern from humans. Recent work in conversational agents has been focused on goal-directed dialogue focused on closed domains such as appointment setting, bank information requests, question-answering, and movie discussion. Natural human conversations are seldom limited in scope and jump from topic to topic, they are laced with metaphor and subtext and face-to-face communication is supplemented with non-verbal cues. Live improvised performance takes natural conversation one step further with multiple actors performing in front of an audience. In improvisation the topic of the conversation is often given by the audience several times during the performance. These suggestions inspire actors to perform novel, unique, and engaging scenes. During each scene, actors must make rapid fire decisions to collaboratively generate coherent narratives. We have embarked on a journey to perform live improvised comedy alongside artificial intelligence systems. We introduce Pyggy and A.L.Ex. (Artificial Language Experiment), the first two Artificial Improvisors, each with a unique composition and embodiment. This work highlights research and development, successes and failures along the way, celebrates collaborations enabling progress, and presents discussions for future work in the space of artificial improvisation.
26
Borderieux, Julien. "Agent conversationnel et pragmatique gricéenne." SHS Web of Conferences 191 (2024): 01001. http://dx.doi.org/10.1051/shsconf/202419101001.
Abstract:
La contribution cherche à montrer l’influence de l’analyse conversationnelle (et notamment celle de la pensée linguistique de Grice, 1975) sur les choix rédactionnels observables dans les productions automatiques de textes argumentatifs par l’agent conversationnel ChatGPT. L’objectif intermédiaire consiste, dans un premier temps, à dégager le substrat de l’analyse conversationnelle anglo-saxonne à l’œuvre dans les réponses de cet agent de conversation, puis à établir les points de concordance entre les textes générés par un agent de conversation comme ChatGPT et les maximes conversationnelles de Grice. Dans un deuxième temps, il s’agira de montrer comment les productions de ce type d’agent conversationnel peuvent être considérées comme des objets gricéens (ces derniers seront dûment définis et on insistera sur l’intérêt de les observer, puisqu’ils contribuent notamment à la classification des textes). Nous ouvrirons à cette occasion le débat sur la notion d’implicature conversationnelle: est-elle ou non pleinement maîtrisée par un robot parleur comme ChatGPT ? Enfin, on proposera un prolongement sur la détection (basée sur l’utilisation systématique et routinière des maximes de Grice) des textes générés exclusivement par un agent conversationnel de ce type: il s’agira de poser la question du repérage des textes produits par des chatbots.
27
Pacella, Massimo, Paride Vasco, Gabriele Papadia, and Vincenzo Giliberti. "An Assessment of Digitalization Techniques in Contact Centers and Their Impact on Agent Performance and Well-Being." Sustainability 16, no. 2 (January 14, 2024): 714. http://dx.doi.org/10.3390/su16020714.
Abstract:
The role of contact centers in improving the operational efficiency of numerous organizations is of utmost importance. Presently, digitalization technology has enabled contact centers to deliver exceptional customer service and support, while minimizing the adverse impact on agent well-being. Artificial intelligence techniques such as topic modeling and sentiment analysis can aid agents in addressing specific queries, providing real-time support and feedback, and helping them build stronger relationships with customers. This study aims to investigate the advantages of integrating these techniques in the analysis of customer–agent conversations within contact centers. This study examines whether there is a discernible advantage in analyzing customer–agent conversations in real-time and whether it is worth using this type of digitization to enhance agent performance and well-being. Furthermore, this study explores the impact of these technologies on European privacy, business, real-time agent support, the value of conversation data, brand reputation, and customer satisfaction. The results of this study demonstrate the significance of incorporating topic modeling and sentiment analysis into the analysis of customer–agent conversations at contact centers.
28
Rodríguez, John Ibañez, Santiago Rocha Durán, Daniel Díaz-López, Javier Pastor-Galindo, and Félix Gómez Mármol. "C3-Sex: A Conversational Agent to Detect Online Sex Offenders." Electronics 9, no. 11 (October 27, 2020): 1779. http://dx.doi.org/10.3390/electronics9111779.
Abstract:
Prevention of cybercrime is one of the missions of Law Enforcement Agencies (LEA) aiming to protect and guarantee sovereignty in the cyberspace. In this regard, online sex crimes are among the principal ones to prevent, especially those where a child is abused. The paper at hand proposes C3-Sex, a smart chatbot that uses Natural Language Processing (NLP) to interact with suspects in order to profile their interest regarding online child sexual abuse. This solution is based on our Artificial Conversational Entity (ACE) that connects to different online chat services to start a conversation. The ACE is designed using generative and rule-based models in charge of generating the posts and replies that constitute the conversation from the chatbot side. The proposed solution also includes a module to analyze the conversations performed by the chatbot and calculate a set of 25 features that describes the suspect’s behavior. After 50 days of experiments, the chatbot generated a dataset with 7199 profiling vectors with the features associated to each suspect. Afterward, we applied an unsupervised method to describe the results that differentiate three groups, which we categorize as indifferent, interested, and pervert. Exhaustive analysis is conducted to validate the applicability and advantages of our solution.
29
Elvir, Miguel, Avelino J. Gonzalez, Christopher Walls, and Bryan Wilder. "Remembering a Conversation – A Conversational Memory Architecture for Embodied Conversational Agents." Journal of Intelligent Systems 26, no. 1 (January 1, 2017): 1–21. http://dx.doi.org/10.1515/jisys-2015-0094.
Abstract:
AbstractThis paper addresses the role of conversational memory in Embodied Conversational Agents (ECAs). It describes an investigation into developing such a memory architecture and integrating it into an ECA. ECAs are virtual agents whose purpose is to engage in conversations with human users, typically through natural language speech. While several works in the literature seek to produce viable ECA dialog architectures, only a few authors have addressed the episodic memory architectures in conversational agents and their role in enhancing their intelligence. In this work, we propose, implement, and test a unified episodic memory architecture for ECAs. We describe a process that determines the prevalent contexts in the conversations obtained from the interactions. The process presented demonstrates the use of multiple techniques to extract and store relevant snippets from long conversations, most of whose contents are unremarkable and need not be remembered. The mechanisms used to store, retrieve, and recall episodes from previous conversations are presented and discussed. Finally, we test our episodic memory architecture to assess its effectiveness. The results indicate moderate success in some aspects of the memory-enhanced ECAs, as well as some work still to be done in other aspects.
30
Sharma, Rajat, Mr Ankur Sharma, and Mr Anurag Rana. "Namah Subjective and Objective Aspects of Conversational Agent." International Journal of Trend in Scientific Research and Development Volume-2, Issue-5 (August 31, 2018): 1303–28. http://dx.doi.org/10.31142/ijtsrd17063.
31
Kovačević, Nikola, Christian Holz, Markus Gross, and Rafael Wampfler. "The Personality Dimensions GPT-3 Expresses During Human-Chatbot Interactions." Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 8, no. 2 (May 13, 2024): 1–36. http://dx.doi.org/10.1145/3659626.
Abstract:
Large language models such as GPT-3 and ChatGPT can mimic human-to-human conversation with unprecedented fidelity, which enables many applications such as conversational agents for education and non-player characters in video games. In this work, we investigate the underlying personality structure that a GPT-3-based chatbot expresses during conversations with a human. We conducted a user study to collect 147 chatbot personality descriptors from 86 participants while they interacted with the GPT-3-based chatbot for three weeks. Then, 425 new participants rated the 147 personality descriptors in an online survey. We conducted an exploratory factor analysis on the collected descriptors and show that, though overlapping, human personality models do not fully transfer to the chatbot's personality as perceived by humans. We also show that the perceived personality is significantly different from that of virtual personal assistants, where users focus rather on serviceability and functionality. We discuss the implications of ever-evolving large language models and the change they affect in users' perception of agent personalities.
32
Pérez-Marín, Diana, and Carlos Caballero. "Using Conceptual Models to Implement Natural Language Pedagogic Agent-Student Conversations." International Journal of Interactive Communication Systems and Technologies 3, no. 2 (July 2013): 29–47. http://dx.doi.org/10.4018/ijicst.2013070103.
Abstract:
The last several decades have seen a growing trend in incorporating pedagogic conversational agents in interactive learning environments. Software systems have increasingly integrated intelligent virtual agents that can interact with students in natural language to fulfill specific tasks such as reviewing content or providing tutor training. The use of an agent-based approach in education has shown many benefits. However, certain design and development issues are still unresolved. This article focuses on the potentials of employing conceptual models to generate agent-student dialog and introduces a new mixed-initiative general domain agent called JARO. The authors report on the procedure for creating the initial conceptual model and discuss its use in guiding agent-student conversations adapted to students' individual learning needs. The stages of implementation of the model as well as the model's viability tested in a proof-of-concept experiment are addressed.
33
Thomas, Paul, Mary Czerwinksi, Daniel Mcduff, and Nick Craswell. "Theories of Conversation for Conversational IR." ACM Transactions on Information Systems 39, no. 4 (October 31, 2021): 1–23. http://dx.doi.org/10.1145/3439869.
Abstract:
Conversational information retrieval is a relatively new and fast-developing research area, but conversation itself has been well studied for decades. Researchers have analysed linguistic phenomena such as structure and semantics but also paralinguistic features such as tone, body language, and even the physiological states of interlocutors. We tend to treat computers as social agents—especially if they have some humanlike features in their design—and so work from human-to-human conversation is highly relevant to how we think about the design of human-to-computer applications. In this article, we summarise some salient past work, focusing on social norms; structures; and affect, prosody, and style. We examine social communication theories briefly as a review to see what we have learned about how humans interact with each other and how that might pertain to agents and robots. We also discuss some implications for research and design of conversational IR systems.
34
Tudor Car, Lorainne, Dhakshenya Ardhithy Dhinagaran, Bhone Myint Kyaw, Tobias Kowatsch, Shafiq Joty, Yin-Leng Theng, and Rifat Atun. "Conversational Agents in Health Care: Scoping Review and Conceptual Analysis." Journal of Medical Internet Research 22, no. 8 (August 7, 2020): e17158. http://dx.doi.org/10.2196/17158.
Abstract:
Background Conversational agents, also known as chatbots, are computer programs designed to simulate human text or verbal conversations. They are increasingly used in a range of fields, including health care. By enabling better accessibility, personalization, and efficiency, conversational agents have the potential to improve patient care. Objective This study aimed to review the current applications, gaps, and challenges in the literature on conversational agents in health care and provide recommendations for their future research, design, and application. Methods We performed a scoping review. A broad literature search was performed in MEDLINE (Medical Literature Analysis and Retrieval System Online; Ovid), EMBASE (Excerpta Medica database; Ovid), PubMed, Scopus, and Cochrane Central with the search terms “conversational agents,” “conversational AI,” “chatbots,” and associated synonyms. We also searched the gray literature using sources such as the OCLC (Online Computer Library Center) WorldCat database and ResearchGate in April 2019. Reference lists of relevant articles were checked for further articles. Screening and data extraction were performed in parallel by 2 reviewers. The included evidence was analyzed narratively by employing the principles of thematic analysis. Results The literature search yielded 47 study reports (45 articles and 2 ongoing clinical trials) that matched the inclusion criteria. The identified conversational agents were largely delivered via smartphone apps (n=23) and used free text only as the main input (n=19) and output (n=30) modality. Case studies describing chatbot development (n=18) were the most prevalent, and only 11 randomized controlled trials were identified. The 3 most commonly reported conversational agent applications in the literature were treatment and monitoring, health care service support, and patient education. Conclusions The literature on conversational agents in health care is largely descriptive and aimed at treatment and monitoring and health service support. It mostly reports on text-based, artificial intelligence–driven, and smartphone app–delivered conversational agents. There is an urgent need for a robust evaluation of diverse health care conversational agents’ formats, focusing on their acceptability, safety, and effectiveness.
35
Jiang, Zhiqiu, Mashrur Rashik, Kunjal Panchal, Mahmood Jasim, Ali Sarvghad, Pari Riahi, Erica DeWitt, Fey Thurber, and Narges Mahyar. "CommunityBots: Creating and Evaluating A Multi-Agent Chatbot Platform for Public Input Elicitation." Proceedings of the ACM on Human-Computer Interaction 7, CSCW1 (April 14, 2023): 1–32. http://dx.doi.org/10.1145/3579469.
Abstract:
In recent years, the popularity of AI-enabled conversational agents or chatbots has risen as an alternative to traditional online surveys to elicit information from people. However, there is a gap in using single-agent chatbots to converse and gather multi-faceted information across a wide variety of topics. Prior works suggest that single-agent chatbots struggle to understand user intentions and interpret human language during a multi-faceted conversation. In this work, we investigated how multi-agent chatbot systems can be utilized to conduct a multi-faceted conversation across multiple domains. To that end, we conducted a Wizard of Oz study to investigate the design of a multi-agent chatbot for gathering public input across multiple high-level domains and their associated topics. Next, we designed, developed, and evaluated CommunityBots - a multi-agent chatbot platform where each chatbot handles a different domain individually. To manage conversation across multiple topics and chatbots, we proposed a novel Conversation and Topic Management (CTM) mechanism that handles topic-switching and chatbot-switching based on user responses and intentions. We conducted a between-subject study comparing CommunityBots to a single-agent chatbot baseline with 96 crowd workers. The results from our evaluation demonstrate that CommunityBots participants were significantly more engaged, provided higher quality responses, and experienced fewer conversation interruptions while conversing with multiple different chatbots in the same session. We also found that the visual cues integrated with the interface helped the participants better understand the functionalities of the CTM mechanism, which enabled them to perceive changes in textual conversation, leading to better user satisfaction. Based on the empirical insights from our study, we discuss future research avenues for multi-agent chatbot design and its application for rich information elicitation.
36
Israfilzade, Khalil. "Conversational marketing as a framework for interaction with the customer: Development & validation of the conversational agent's usage scale." Journal of Life Economics 8, no. 4 (October 31, 2021): 533–46. http://dx.doi.org/10.15637/jlecon.8.4.12.
Abstract:
Conversational agents are becoming an essential part of a growing number of personal and commercial encounters, bringing the issue of Conversational Marketing to a broader audience. A conversational agent is a developing technology that will be used in various fields throughout life, including e-commerce. The common characteristics of any conversational agent in whatever area are their capacity to engage in one-to-one personalised real-time dialogue with a human user and their availability 24 hours a day. Scale items for conversational agent phenomena have not been created scientifically or managerially in a business environment. The primary goal of this study was to develop and validate a new scale for conversational agents that could be used to quantify individual interactions in conversational marketing. As a result, the creation of a new scale for conversational agents with the objective of measuring individual customer interactions in conversational marketing was separated into two phases: Scale Development and Scale Validation. The Conversational Agent Usage Scale was developed and validated as a consequence of pilot studies. Additionally, this article discusses the practical consequences of conversational marketing, which can now be accomplished through the use of the Conversational Agent Usage Scale, which may be used by Customer Service & Support, Marketing, and Sales departments.
37
Omarov, Batyrkhan, Sergazi Narynov, Zhandos Zhumanov, Elmira Alzhanova, Aidana Gumar, and Mariyam Khassanova. "Artificial intelligence enabled conversational agent for mental healthcare." International journal of health sciences 6, no. 3 (October 5, 2022): 1544–55. http://dx.doi.org/10.53730/ijhs.v6n3.13239.
Abstract:
Conversational agents are a software program that can converse with users in the manner of a real-world conversation. Artificial intelligence (AI) is not complete without conversation modeling. The most difficult artificial intelligence endeavor since its start has been developing an effective chatbot application. Despite chatbots may do a variety of tasks, their main duty is to accurately understand human speech and respond appropriately. Previously, manual patterns and instructions or simple statistical methods were used to create chatbots architectures. Due to its improved capacity for training, end-to-end AI has replaced these models since 2015. The most popular technique for conversation simulation at the moment is the encoder-decoder recurrent neural network (RNN). The realm of language comprehension served as inspiration for this design. Until recently, a number of additions and changes dramatically enhanced chatbot conversational abilities. In this paper, we outline our research results into creating an interactive digital chatbot that may provide patients with psychological assistance. To build and train the chatbot, we used resources such Rasa Natural Language Processing (NLU) technology, which employs natural language processing (NLP) methods. The results of the investigation showed that selecting proper responses while conversing with patients had a more than 70% predictive performance.
38
Kim, Hyounghun, Doo Soon Kim, Seunghyun Yoon, Franck Dernoncourt, Trung Bui, and Mohit Bansal. "CAISE: Conversational Agent for Image Search and Editing." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 10 (June 28, 2022): 10903–11. http://dx.doi.org/10.1609/aaai.v36i10.21337.
Abstract:
Demand for image editing has been increasing as users' desire for expression is also increasing. However, for most users, image editing tools are not easy to use since the tools require certain expertise in photo effects and have complex interfaces. Hence, users might need someone to help edit their images, but having a personal dedicated human assistant for every user is impossible to scale. For that reason, an automated assistant system for image editing is desirable. Additionally, users want more image sources for diverse image editing works, and integrating an image search functionality into the editing tool is a potential remedy for this demand. Thus, we propose a dataset of an automated Conversational Agent for Image Search and Editing (CAISE). To our knowledge, this is the first dataset that provides conversational image search and editing annotations, where the agent holds a grounded conversation with users and helps them to search and edit images according to their requests. To build such a system, we first collect image search and editing conversations between pairs of annotators. The assistant-annotators are equipped with a customized image search and editing tool to address the requests from the user-annotators. The functions that the assistant-annotators conduct with the tool are recorded as executable commands, allowing the trained system to be useful for real-world application execution. We also introduce a generator-extractor baseline model for this task, which can adaptively select the source of the next token (i.e., from the vocabulary or from textual/visual contexts) for the executable command. This serves as a strong starting point while still leaving a large human-machine performance gap for useful future work. Data and code are available: https://github.com/hyounghk/CAISE.
39
Kapuskar, Vaibhavi, Sakshi Bobade, Srushti Diwan, Akshata Dholwade, Vaishnavi Kamble, and Prof S. R. Gudadhe. "Efficient Chatbot Designing." International Journal for Research in Applied Science and Engineering Technology 10, no. 4 (April 30, 2022): 2743–45. http://dx.doi.org/10.22214/ijraset.2022.41889.
Abstract:
Abstract: A conversational agent (chatbot) is a piece of software that is able to communicate with humans using natural language. Modeling conversation is an important task in natural language processing and artificial intelligence (AI). Indeed, ever since the birth of AI, creating a good chatbot remains one of the field’s hardest challenges. While chatbots can be used for various tasks, in general they have to understand users’ utterances and provide responses that are relevant to the problem at hand. In the past, methods for constructing chatbot architectures have relied on hand-written rules and templates or simple statistical methods. With the rise of deep learning these models were quickly replaced by end-to-end trainable neural networks around 2015. More specifically, the recurrent encoder-decoder model [Cho et al., 2014] dominates the task of conversational modeling. This architecture was adapted from the neural machine translation domain, where it performs extremely well. Since then a multitude of variations and features were presented that augment the quality of the conversation that chatbots are capable of the next section of my paper focuses on adapting the very recent Tranformer [Vaswani et al., 2017] model to the chatbot domain, which is currently the state-of-the-art in neural machine translation. I first present my experiments with the vanilla model, using conversations extracted from the Cornell Movie-Dialog Corpus [Danescu-Niculescu-Mizil and Lee, 2011]. Secondly, I augment the model with some of my ideas regarding the issues of encoder-decoder architectures. More specifically, I feed additional features into the model like mood or persona together with the raw conversation data. Finally, I conduct a detailed analysis of how the vanilla model performs on conversational data by comparing it to previous chatbot models and how the additional features, affect the quality of the generated responses
40
Mooney Berges, Bethany, Christine Cambareri, Samuel U. Takvorian, Mike Serpa, Lawrence N. Shulman, Justin E. Bekelman, Katharine A. Rendle, Jesse Argon, and Roy Rosin. "Leveraging a conversational agent to support adherence to oral anticancer agents: A usability study." Journal of Clinical Oncology 37, no. 15_suppl (May 20, 2019): 6534. http://dx.doi.org/10.1200/jco.2019.37.15_suppl.6534.
Abstract:
6534 Background: Identifying effective, scalable strategies to ensure patient adherence to oral anticancer agents (OACAs) is a major challenge. Previous studies have shown widely variable rates of adherence, and suboptimal adherence is associated with decreased effectiveness and higher costs. A small but growing literature supports digital health behavioral interventions across a variety of chronic illnesses, including in cancer. In particular, conversational agents—or technologies that mimic human conversation using text or spoken language—have shown early promise in supporting behavior change, but have yet to be rigorously tested in the context of OACAs. Methods: A rapid cycle prototyping approach led to the development of ‘Penny’ – a bidirectional, conversational agent that engages patients via text messaging, and leverages natural language processing and machine learning to learn from clinical interactions. Core functionalities include: (1) real-time dosing instructions, (2) motivational reminders, and (3) symptom monitoring with self-management support. We conducted a four-month usability study between December 24, 2017 and May 1, 2018 in a large academic cancer center. At monthly intervals for the first 12 weeks of follow-up, research staff conducted qualitative interviews with participants to evaluate usability and acceptance. Results: 11 patients with gastrointestinal neuroendocrine cancer on capecitabine and temozolomide were approached regarding the study. Of these, 10 agreed to participate (ages 45 to 71). Overall, participant satisfaction was high with a Net Promoter Score of 100. Reliability of Penny’s algorithmic branching to provide accurate dosing information and symptom triage was also high: symptoms were accurately graded 100% of the time, and there was appropriate self-management advice or provider triage 100% of the time. Average daily adherence (based on self-report) was 98%. Participants reported that 3 emergency room visits were avoided during the study period. Conclusions: In preliminary testing, a mobile phone-based conversational agent was a usable and acceptable means of supporting OACA adherence. Expanded study testing patient safety and efficacy is underway.
41
Khan, Imran ullah, Junaid Javed, Ahthasham Sajid, Shahnoor, and Iqra Tabassum. "Comparative Analysis of Classical and Neural Networks based ChatBot’s Techniques." Sir Syed University Research Journal of Engineering & Technology 13, no. 1 (June 28, 2023): 61–73. http://dx.doi.org/10.33317/ssurj.508.
Abstract:
Conversational agents like Alexa from Amazon, Siri from Apple, Assistant from Google, and Cortana from Microsoft demonstrate extraordinary research and potential in conversational agents. A conversational agent, chatter-bot, or chatbot is a piece of computer software supposed to communicate at a level of intelligence comparable to a person's. Chatbots are designed for various purposes, such as task-oriented helpers and creators of open-ended discourse. Numerous approaches have been studied, from primitive types of hard-coded response generators to contemporary ways of constructing artificial intelligence. These are classified as rule-based or neural network-based systems. Unlike the rule-based technique, which is based on pre-defined templates and responses, the neural network approach is based on deep learning models. Rule-based communication is optimal for more straightforward, task-oriented conversations. Open-domain conversational modeling is a more complicated topic that depends heavily on neural network techniques. This article begins with an overview of chatbots before diving into the specifics of a variety of traditional, rule-based, and neural network-based methods. A table summarising previous field research closes the survey. It looks at the most recent and vital research on the subject, the evaluation instruments used areas for improvement, and the applicability of the proposed methods.
42
Bennion, Matthew Russell, Gillian E. Hardy, Roger K. Moore, Stephen Kellett, and Abigail Millings. "Usability, Acceptability, and Effectiveness of Web-Based Conversational Agents to Facilitate Problem Solving in Older Adults: Controlled Study." Journal of Medical Internet Research 22, no. 5 (May 27, 2020): e16794. http://dx.doi.org/10.2196/16794.
Abstract:
Background The usability and effectiveness of conversational agents (chatbots) that deliver psychological therapies is under-researched. Objective This study aimed to compare the system usability, acceptability, and effectiveness in older adults of 2 Web-based conversational agents that differ in theoretical orientation and approach. Methods In a randomized study, 112 older adults were allocated to 1 of the following 2 fully automated interventions: Manage Your Life Online (MYLO; ie, a chatbot that mimics a therapist using a method of levels approach) and ELIZA (a chatbot that mimics a therapist using a humanistic counseling approach). The primary outcome was problem distress and resolution, with secondary outcome measures of system usability and clinical outcome. Results MYLO participants spent significantly longer interacting with the conversational agent. Posthoc tests indicated that MYLO participants had significantly lower problem distress at follow-up. There were no differences between MYLO and ELIZA in terms of problem resolution. MYLO was rated as significantly more helpful and likely to be used again. System usability of both the conversational agents was associated with helpfulness of the agents and the willingness of the participants to reuse. Adherence was high. A total of 12% (7/59) of the MYLO group did not carry out their conversation with the chatbot. Conclusions Controlled studies of chatbots need to be conducted in clinical populations across different age groups. The potential integration of chatbots into psychological care in routine services is discussed.
43
Fadhil, Ahmed, Yunlong Wang, and Harald Reiterer. "Assistive Conversational Agent for Health Coaching: A Validation Study." Methods of Information in Medicine 58, no. 01 (May 22, 2019): 009–23. http://dx.doi.org/10.1055/s-0039-1688757.
Abstract:
Objective Poor lifestyle represents a health risk factor and is the leading cause of morbidity and chronic conditions. The impact of poor lifestyle can be significantly altered by individual's behavioral modification. Although there are abundant lifestyle promotion applications and tools, they are still limited in providing tailored social support that goes beyond their predefined functionalities. In addition, virtual coaching approaches are still unable to handle user emotional needs. Our approach presents a human–virtual agent mediated system that leverages the conversational agent to handle menial caregiver's works by engaging users (e.g., patients) in a conversation with the conversational agent. The dialog used a natural conversation to interact with users, delivered by the conversational agent and handled with a finite state machine automaton. Our research differs from existing approaches that replace a human coach with a fully automated assistant on user support. The methodology allows users to interact with the technology and access health-related interventions. To assist physicians, the conversational agent gives weighting to user's adherence, based on prior defined conditions. Materials and Methods This article describes the design and validation of CoachAI, a conversational agent-assisted health coaching system to support health intervention delivery to individuals or groups. CoachAI instantiates a text-based health care conversational agent system that bridges the remote human coach and the users. Results We will discuss our approach and highlight the outcome of a 1-month validation study on physical activity, healthy diet, and stress coping. The study validates technology aspects of our human–virtual agent mediated health coaching system. We present the intervention settings and findings from the study. In addition, we present some user-experience validation results gathered during or after the experimentation. Conclusions The study provided a set of dimensions when building a human–conversational agent powered health intervention tool. The results provided interesting insights when using human–conversational agent mediated approach in health coaching systems. The findings revealed that users who were highly engaged were also more adherent to conversational-agent activities. This research made key contributions to the literature on techniques in providing social, yet tailored health coaching support: (1) identifying habitual patterns to understand user preferences; (2) the role of a conversational agent in delivering health promoting microactivities; (3) building the technology while adhering to individuals' daily messaging routine; and (4) a socio-technical system that fits with the role of conversational agent as an assistive component. Future Work Future improvements will consider building the activity recommender based on users' interaction data and integrating users' dietary pattern and emotional wellbeing into the initial user clustering by leveraging information and communication technology approaches (e.g., machine learning). We will integrate a sentiment analysis capability to gather further data about individuals and report these data to the caregiver.
44
Young, Tom, Frank Xing, Vlad Pandelea, Jinjie Ni, and Erik Cambria. "Fusing Task-Oriented and Open-Domain Dialogues in Conversational Agents." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 10 (June 28, 2022): 11622–29. http://dx.doi.org/10.1609/aaai.v36i10.21416.
Abstract:
The goal of building intelligent dialogue systems has largely been separately pursued under two paradigms: task-oriented dialogue (TOD) systems, which perform task-specific functions, and open-domain dialogue (ODD) systems, which focus on non-goal-oriented chitchat. The two dialogue modes can potentially be intertwined together seamlessly in the same conversation, as easily done by a friendly human assistant. Such ability is desirable in conversational agents, as the integration makes them more accessible and useful. Our paper addresses this problem of fusing TODs and ODDs in multi-turn dialogues. Based on the popular TOD dataset MultiWOZ, we build a new dataset FusedChat, by rewriting the existing TOD turns and adding new ODD turns. This procedure constructs conversation sessions containing exchanges from both dialogue modes. It features inter-mode contextual dependency, i.e., the dialogue turns from the two modes depend on each other. Rich dependency patterns such as co-reference and ellipsis are included. The new dataset, with 60k new human-written ODD turns and 5k re-written TOD turns, offers a benchmark to test a dialogue model's ability to perform inter-mode conversations. This is a more challenging task since the model has to determine the appropriate dialogue mode and generate the response based on the inter-mode context. However, such models would better mimic human-level conversation capabilities. We evaluate two baseline models on this task, including the classification-based two-stage models and the two-in-one fused models. We publicly release FusedChat and the baselines to propel future work on inter-mode dialogue systems.
45
Roberts, Seán G., and Stephen C. Levinson. "Conversation, cognition and cultural evolution." Interaction Studies 18, no. 3 (December 8, 2017): 402–42. http://dx.doi.org/10.1075/is.18.3.06rob.
Abstract:
This paper outlines a first attempt to model the special constraints that arise in language processing in conversation, and to explore the implications such functional considerations may have on language typology and language change. In particular, we focus on processing pressures imposed by conversational turn-taking and their consequences for the cultural evolution of the structural properties of language. We present an agent-based model of cultural evolution where agents take turns at talk in conversation. When the start of planning for the next turn is constrained by the position of the verb, the stable distribution of dominant word orders across languages evolves to match the actual distribution reasonably well. We suggest that the interface of cognition and interaction should be a more central part of the story of language evolution.
46
Lee, Kyung-A., and Soon-Bum Lim. "Designing a Leveled Conversational Teachable Agent for English Language Learners." Applied Sciences 13, no. 11 (May 27, 2023): 6541. http://dx.doi.org/10.3390/app13116541.
Abstract:
Given the considerable importance of the English language as a common method of global communication, supporting and engaging learning environments for studying English as a second language are essential. In this study, we propose an interactive agent that considers differences in learners’ skill levels to help motivate learners and support independent study. The proposed agent is an AI chatbot that can vary the complexity of its natural language interactions as learners’ skills improve and engage in unstructured conversations with users. We first collected a dataset of English conversations among children and then acquired data on learners’ utterances of words and sentences using an interactive interface for skill evaluation. Based on these datasets, we generated a set of personalized conversational agents by using algorithms to evaluate speakers’ pronunciation and sentences. Finally, an expert in English language learning evaluated the interactive system to ensure that it could support learners with different levels of proficiency and that the application may be expected to help motivate students to learn. The results showed that the interactive teachable agent could help motivate students who may not otherwise be interested in learning by using a more personalized approach tailored to their skill level.
47
Liu, Xiulong, Sudipta Paul, Moitreya Chatterjee, and Anoop Cherian. "CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 4 (March 24, 2024): 3765–73. http://dx.doi.org/10.1609/aaai.v38i4.28167.
Abstract:
Audio-visual navigation of an agent towards locating an audio goal is a challenging task especially when the audio is sporadic or the environment is noisy. In this paper, we present CAVEN, a Conversation-based Audio-Visual Embodied Navigation framework in which the agent may interact with a human/oracle for solving the task of navigating to an audio goal. Specifically, CAVEN is modeled as a budget-aware partially observable semi-Markov decision process that implicitly learns the uncertainty in the audio-based navigation policy to decide when and how the agent may interact with the oracle. Our CAVEN agent can engage in fully-bidirectional natural language conversations by producing relevant questions and interpret free-form, potentially noisy responses from the oracle based on the audio-visual context. To enable such a capability, CAVEN is equipped with: i) a trajectory forecasting network that is grounded in audio-visual cues to produce a potential trajectory to the estimated goal, and (ii) a natural language based question generation and reasoning network to pose an interactive question to the oracle or interpret the oracle's response to produce navigation instructions. To train the interactive modules, we present a large scale dataset: AVN-Instruct, based on the Landmark-RxR dataset. To substantiate the usefulness of conversations, we present experiments on the benchmark audio-goal task using the SoundSpaces simulator under various noisy settings. Our results reveal that our fully-conversational approach leads to nearly an order-of-magnitude improvement in success rate, especially in localizing new sound sources and against methods that use only uni-directional interaction.
48
Castilla, Eugenia, Juan José Escobar, Claudia Villalonga, and Oresti Banos. "HIGEA: An Intelligent Conversational Agent to Detect Caregiver Burden." International Journal of Environmental Research and Public Health 19, no. 23 (November 30, 2022): 16019. http://dx.doi.org/10.3390/ijerph192316019.
Abstract:
Mental health disorders increasingly affect people worldwide. As a consequence, more families and relatives find themselves acting as caregivers. Most often, these are untrained people who experience loneliness, abandonment, and often develop signs of depression (i.e., caregiver burden syndrome). In this work, we present HIGEA, a digital system based on a conversational agent to help to detect caregiver burden. The conversational agent naturally embeds psychological test questions into informal conversations, which aim at increasing the adherence of use and avoiding user bias. A proof-of-concept is developed based on the popular Zarit Test, which is widely used to assess caregiver burden. Preliminary results show the system is useful and effective.
49
Beinema, Tessa, Harm op den Akker, Dennis Hofs, and Boris van Schooten. "The WOOL Dialogue Platform: Enabling Interdisciplinary User-Friendly Development of Dialogue for Conversational Agents." Open Research Europe 2 (January 13, 2022): 7. http://dx.doi.org/10.12688/openreseurope.14279.1.
Abstract:
Health coaching applications can include (embodied) conversational agents as coaches. The development of these agents requires an interdisciplinary cooperation between eHealth application developers, interaction designers and domain experts. Therefore, proper dialogue authoring tools and tools to integrate these dialogues in a conversational agent system are essential in the process of creating successful agent-based applications. However, we found no existing open source, easy-to-use authoring tools that support multidisciplinary agent development. To that end, we developed the WOOL Dialogue Platform. The WOOL Dialogue Platform provides the eHealth and conversational agent communities with an open source platform, consisting of a set of easy to use tools that facilitate virtual agent development. The platform consists of a dialogue definition language, an editor, application development libraries and a web service. To illustrate the platform’s possibilities and use in practice, we describe two use cases from EU Horizon 2020 research projects. The WOOL Dialogue Platform is an ‘easy to use, and powerful if needed’ platform for the development of conversational agent applications that is seeing a slow but steady increase in uptake in the eHealth community. Developed to support dialogue authoring for embodied conversational agents in the health coaching domain, this platform’s strong points are its ease of use and ability to let domain experts and agents technology experts work together by providing all parties with tools that support their work effectively.
50
Gassen, Marius, Benjamin Hättasch, Benjamin Hilprecht, Nadja Geisler, Alexander Fraser, and Carsten Binnig. "Demonstrating CAT." Proceedings of the VLDB Endowment 15, no. 12 (August 2022): 3586–89. http://dx.doi.org/10.14778/3554821.3554850.
Abstract:
Databases for OLTP are often the backbone for applications such as hotel room or cinema ticket booking applications. However, developing a conversational agent (i.e., a chatbot-like interface) to allow end-users to interact with an application using natural language requires both immense amounts of training data and NLP expertise. This motivates CAT , which can be used to easily create conversational agents for transactional databases. The main idea is that, for a given OLTP database, CAT uses weak supervision to synthesize the required training data to train a state-of-the-art conversational agent, allowing users to interact with the OLTP database. Furthermore, CAT provides an out-of-the-box integration of the resulting agent with the database. As a major difference to existing conversational agents, agents synthesized by CAT are data-aware. This means that the agent decides which information should be requested from the user based on the current data distributions in the database, which typically results in markedly more efficient dialogues compared with non-data-aware agents. We publish the code for CAT as open source.