From Eliza to XiaoIce: challenges and opportunities with social chatbots
Open accessThe DOI matches its Crossref record; 81 of the 94 references it cites were found in a registry or an index.
Abstract
Conversational systems have come a long way since their inception in the 1960s. After decades of research and development, we have seen progress from Eliza and Parry in the 1960s and 1970s, to task-completion systems as in the Defense Advanced Research Projects Agency (DARPA) communicator program in the 2000s, to intelligent personal assistants such as Siri, in the 2010s, to today’s social chatbots like XiaoIce. Social chatbots’ appeal lies not only in their ability to respond to users’ diverse requests, but also in being able to establish an emotional connection with users. The latter is done by satisfying users’ need for communication, affection, as well as social belonging. To further the advancement and adoption of social chatbots, their design must focus on user engagement and take both intellectual quotient (IQ) and emotional quotient (EQ) into account. Users should want to engage with a social chatbot; as such, we define the success metric for social chatbots as conversation-turns per session (CPS). Using XiaoIce as an illustrative example, we discuss key technologies in building social chatbots from core chat to visual awareness to skills. We also show how XiaoIce can dynamically recognize emotion and engage the user throughout long conversations with appropriate interpersonal responses. As we become the first generation of humans ever living with artificial intelligenc (AI), we have a responsibility to design social chatbots to be both useful and empathetic, so they will become ubiquitous and help society as a whole.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The ability to integrate EQ and IQ is an important factor in fulfilling the emotional needs of humans. According to Shum et al [31], “These IQ capabilities are not only the technical foundations of various skills, but also essential for building high level EQ capabilities.””
From User Experiences of Social Support From Companion Chatbots in Everyday Contexts: Thematic Analysis (2020) · cites this paper as [31]
In the citing paper
“behaviors that have been historically very difficult to accurately capture in AI, but are essential if AI is to serve as effective companions for humans [31]”
From User Experiences of Social Support From Companion Chatbots in Everyday Contexts: Thematic Analysis (2020) · cites this paper as [31]
In the citing paper
“Studies of social chatbots such as XiaoIce (Shum et al., 2018) and Replika (Ta et al., 2020) and the mental health chatbots Woebot (Fitzpatrick et al., 2017) and Tess (Fulmer et al., 2018) demonstrate that chatbots may induce a sense of a relationship in users.”
From My Chatbot Companion - a Study of Human-Chatbot Relationships (2021) · cites this paper as Shum et al., 2018
In the citing paper
“From the emergence of the first chatbot, ELIZA, developed by Joseph Weizenbaum (1966), chatbots have been trying to ‘mimic human behaviour in a text-based conversation’ (Shum et al. 2018, p. 10; Abd-Alrazaq et al. 2020).”
From Chatbot breakthrough in the 2020s? An ethical reflection on the trend of automated consultations in health care (2022) · cites this paper as Shum et al. 2018
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“, 2016), computer vision (Krizhevsky et al., 2012; He et al., 2016), information retrieval (Huang et al.”
BackgroundImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 2×
“, 2016), computer vision (Krizhevsky et al., 2012; He et al., 2016), information retrieval (Huang et al.”
BackgroundHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 3×
“These representation vectors are then fed into a decoder, usually another LSTM, to generate the response word-by-word (Vinyals and Le, 2015).”
BackgroundMaslow, A. H. (1943) · Psychological Review · doi:10.1037/h0054346 · Cited by 21,563 · cited 2×
“Unlike early chatbots designed for chitchat, social chatbots are created to serve users’ needs for communication, affection, and social belonging (Maslow, 1943) rather than for passing the Turing Test.”
BackgroundSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 3×
“…perceptual and cognitive AI technologies, e.g., natural language understanding (Bengio et al., 2001; Mikolov et al., 2013; Sutskever et al., 2014; Bahdanau et al., 2015; Mesnil et al., 2015), speech recognition and synthesis (Hinton et al., 2012; Deng et al., 2013; Xiong et al., 2016; Qian et…”
BackgroundMethodFrames of Mind: The Theory of Multiple Intelligences
Klitgaard, R., & Gardner, H. (1984) · Journal of Policy Analysis and Management · doi:10.2307/3324560 · Cited by 13,636
(2017) · Defining and Classifying Children in Need · doi:10.4324/9781315258324-16 · Cited by 11,320
I.—COMPUTING MACHINERY AND INTELLIGENCE
TURING, A. M. (1950) · Mind · doi:10.1093/mind/lix.236.433 · Cited by 10,290 · cited 4×
“Unlike early chatbots designed for chitchat, social chatbots are created to serve users’ needs for communication, affection, and social belonging (Maslow, 1943) rather than for passing the Turing Test.”
BackgroundMethodInfluentialHinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260 · cited 2×
“, 2013, 2015), speech recognition and synthesis (Hinton et al., 2012; Deng et al., 2013; Qian et al., 2014; van den Oord et al., 2016; Xiong et al., 2016), computer vision (Krizhevsky et al.”
Background
Research works printed but not linked: 8
- Bengio, 2003, A neural probabilistic language model, 1137
- 10.1016/0004-3702(71)90002-6 · DOI · Paper page
- 10.21437/icslp.2000-224 · DOI
- 10.18653/v1/P16-1094 · DOI · Paper page
- Mikolov, 2013, Distributed representations of words and phrases and their compositionality, 3111
- 10.21437/Eurospeech.1999-389 · doi:10.21437/eurospeech.1999-389
- 10.18653/v1/e17-1042 · DOI · Paper page
- Yu, 2016, Chatbot evaluation and database expansion via crowdsourcing
Cited by
Chatbots: History, technology, and applications
Adamopoulou, E., & Moussiades, L. (2020) · Machine Learning with Applications · doi:10.1016/j.mlwa.2020.100006 · Cited by 1,090
My Chatbot Companion - a Study of Human-Chatbot Relationships
Skjuve, M., Følstad, A., Fostervold, K. I., & Brandtzaeg, P. B. (2021) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2021.102601 · Cited by 797
“XiaoIce, launched in 2014, is designed for long-term affective engagement with users and has reached 660 million active users (Zhou et al., 2018).”
BackgroundRecipes for Building an Open-Domain Chatbot
Roller, S., Dinan, E., Goyal, N., Ju, D., Williamson, M., Liu, Y., Xu, J., Ott, M., Smith, E. M., Boureau, Y.-L., et al. (2021) · Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · doi:10.18653/v1/2021.eacl-main.24 · Cited by 784
Recipes for building an open-domain chatbot
Roller, S., Dinan, E., Goyal, N., Ju, D., Williamson, M., Liu, Y., Xu, J., Ott, M., Shuster, K., Smith, E. M., et al. (2020) · arXiv · doi:10.48550/arxiv.2004.13637 · Cited by 784
“, 2019), Mitsuku5, Cleverbot6, and XiaoIce (Shum et al., 2018; Zhou et al., 2020).”
MethodThe design and implementation of Xiaoice, an empathetic social chatbot
Zhou, L., Gao, J., Li, D., & Shum, H.-Y. (2020) · Computational Linguistics · doi:10.1162/coli_a_00368 · Cited by 777
“Systems BLEU-4 ROUGE-L CIDEr-D METEOR SPICE LSTM-XE Vinyals et al. [2015] 2.”
BackgroundSelf-citationThe Design and Implementation of XiaoIce, an Empathetic Social Chatbot
Zhou, L., Gao, J., Li, D., & Shum, H.-Y. (2018) · arXiv · doi:10.48550/arxiv.1812.08989 · Cited by 777
Self-citationChaves, A. P., & Gerosa, M. A. (2021) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2020.1841438 · Cited by 572
“According to [Shum et al. 2018], leveraging the context can also help to smoothly guide the user to a target topic.”
BackgroundMethodInfluentialMultimodal intelligence: Representation learning, information fusion, and applications
Zhang, C., Yang, Z., He, X., & Deng, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2987728 · Cited by 511
“as intelligent personal assistant systems that must understand human communication based on spoken words, body language, and pictorial languages [34].”
BackgroundSelf-citationA Literature Survey of Recent Advances in Chatbots
Caldarini, G., Jaf, S., & McGarry, K. (2022) · Information · doi:10.3390/info13010041 · Cited by 470
“It is thus a simple yet widely general and flexible model that can be used to solve different NLP tasks [16,34].”
BackgroundInfluentialUser Experiences of Social Support From Companion Chatbots in Everyday Contexts: Thematic Analysis
Ta, V., Griffith, C., Boatfield, C., Wang, X., Civitello, M., Bader, H., DeCero, E., & Loggarakis, A. (2020) · Journal of Medical Internet Research · doi:10.2196/16235 · Cited by 561
“…interpersonal behaviors such as understanding context, identifying user emotions, and remembering content from previous conversations—behaviors that have been historically very difficult to accurately capture in AI, but are essential if AI is to serve as effective companions for humans [31].”
BackgroundArtificially intelligent chatbots in digital mental health interventions: a review
Boucher, E. M., Harake, N. R., Ward, H. E., Stoeckl, S. E., Vargas, J., Minkel, J., Parks, A. C., & Zilca, R. (2021) · Expert Review of Medical Devices · doi:10.1080/17434440.2021.2013200 · Cited by 440
“User input is primarily written, via open text or multiple-choice options, while output generated by the chatbot can be written, spoken, or visual [69].”
BackgroundBekbolatova, M., Mayer, J., Ong, C. W., & Toma, M. (2024) · Healthcare · doi:10.3390/healthcare12020125 · Cited by 404
“Eliza could engage in conversations with humans by utilizing pattern matching to generate appropriate responses based on textual inputs [5].”
BackgroundZhang, J., Oh, Y. J., Lange, P., Yu, Z., & Fukuoka, Y. (2020) · Journal of Medical Internet Research · doi:10.2196/22845 · Cited by 363
“We conceptualize behavior change chatbots as a type of persuasive technology [14], which is more complicated than designing a social chatbot to engage in general conversations (eg, talking about movies or weather) [47].”
Artificial Intelligence in Tactical Human Resource Management: A Systematic Literature Review
Votto, A. M., Valecha, R., Najafirad, P., & Rao, H. R. (2021) · International Journal of Information Management Data Insights · doi:10.1016/j.jjimei.2021.100047 · Cited by 322
Croes, E. A. J., & Antheunis, M. L. (2021) · Journal of Social and Personal Relationships · doi:10.1177/0265407520959463 · Cited by 291
“Finally, there are social chatbots acting like companions with whom people can socially interact (e.g., Mitsuku; Shum et al., 2018).”
BackgroundInfluentialChallenges in building intelligent open-domain dialog systems
Huang, M., Zhu, X., & Gao, J. (2020) · ACM Transactions on Information Systems · doi:10.1145/3383123 · Cited by 288
“variety of topics for hours [126, 192].”
BackgroundParagraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks
Zhao, Y., Ni, X., Ding, Y., & Ke, Q. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1424 · Cited by 281
“A conversational system can be proactive by asking the user questions (Shum et al., 2018), while a QnA system can benefit from a large scale question-answering corpus which can be created by an automated QG system (Duan et al., 2017).”
BackgroundImplementation of an AI chatbot as an English conversation partner in EFL speaking classes
Yang, H., Kim, H., Lee, J. H., & Shin, D. (2022) · ReCALL · doi:10.1017/s0958344022000039 · Cited by 276
“Task success rate is another metric used to measure chatbots ’ performance (Shum et al ., 2018).”
BackgroundMethodDeep reinforcement learning: a survey
Wang, H.-N., Liu, N., Zhang, Y.-Y., Feng, D.-W., Huang, F., Li, D.-S., & Zhang, Y.-M. (2020) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1900533 · Cited by 274
“The task of chatbots in dialogue systems is to mimic human-human interactions with extended conversations (Shum et al., 2018).”
BackgroundSelf-citationChatbots, Humbots, and the Quest for Artificial General Intelligence
Grudin, J., & Jacques, R. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300439 · Cited by 275
“And developers of virtual companions such as Xiaoice and Zo add to their repertoires of skills to maintain user interest [30].”
BackgroundUsers' experiences with chatbots: findings from a questionnaire study
Følstad, A., & Brandtzaeg, P. B. (2020) · Quality and User Experience · doi:10.1007/s41233-020-00033-2 · Cited by 252
“For chatbots oriented towards social interaction [42], pragmatic attributes of user experience are typically less emphasized.”
BackgroundAbdulquadri, A., Mogaji, E., Kieu, T. A., & Nguyen, N. P. (2021) · Journal of Enterprising Communities: People and Places in the Global Economy · doi:10.1108/jec-06-2020-0126 · Cited by 248
Future directions for chatbot research: An interdisciplinary research agenda
Følstad, A., Araujo, T., Law, E. L.-C., Brandtzaeg, P. B., Papadopoulos, S., Reis, L., Baez, M., Laban, G., McAllister, P., Ischen, C., et al. (2021) · Computing · doi:10.1007/s00607-021-01016-7 · Cited by 247
Social companionship with artificial intelligence: Recent trends and future avenues
Chaturvedi, R., Verma, S., Das, R., & Dwivedi, Y. K. (2023) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2023.122634 · Cited by 244
Emerging-market consumers’ interactions with banking chatbots
Mogaji, E., Balakrishnan, J., Nwoba, A. C., & Nguyen, N. P. (2021) · Telematics and Informatics · doi:10.1016/j.tele.2021.101711 · Cited by 235
How may I help you? Driving brand engagement through the warmth of an initial chatbot message
Kull, A. J., Romero, M., & Monahan, L. (2021) · Journal of Business Research · doi:10.1016/j.jbusres.2021.03.005 · Cited by 237
To chat or bot to chat: Ethical issues with using chatbots in mental health
Coghlan, S., Leins, K., Sheldrick, S., Cheong, M., Gooding, P., & D'Alfonso, S. (2023) · DIGITAL HEALTH · doi:10.1177/20552076231183542 · Cited by 215
“Microsoft, for example, suggest that ‘[s]ocial chatbots’ appeal lies not only in their ability to respond to users’ diverse requests, but also in being able to establish an emotional connection with users’ and so ‘better understand them and therefore help them over a long period of time’.(24) In the 1950s, Alan Turing…”
BackgroundLarge Language Models for Information Retrieval: A Survey
Zhu, Y., Yuan, H., Wang, S., Liu, J., Liu, W., Deng, C., Chen, H., Liu, Z., Dou, Z., & Wen, J.-R. (2026) · ACM Transactions on Information Systems · doi:10.1145/3748304 · Cited by 225
“In dialogue systems (chatbots) [1, 5– 8], such as Microsoft Xiaoice [2], Apple Siri, 1 and Google Assistant, 2 IR systems play a crucial role in retrieving appropriate responses to user input utterances, thereby producing natural and fluent human-machine conversations.”
Neural Approaches to Conversational AI
Gao, J., Galley, M., & Li, L. (2019) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000074 · Cited by 209
Advantages and constraints of a hybrid model K–12 e-learning assistant chatbot
Wu, E. H.-K., Lin, C.-H., Ou, Y.-Y., Liu, C.-Z., Wang, W.-K., & Chao, C.-Y. (2020) · IEEE Access · doi:10.1109/access.2020.2988252 · Cited by 205
“These AI advancements show that early rule-based dialogue or conversational systems like Eliza and Alice mentioned in [19] could be greatly improved by machine learning.”
BackgroundThomaz, F., Salge, C., Karahanna, E., & Hulland, J. (2020) · Journal of the Academy of Marketing Science · doi:10.1007/s11747-019-00704-3 · Cited by 204
“7 According to Shum et al. (2018, p. 6), a CA “ may generate responses in attractive styles (e.g., having a sense of humor) that improve user engagement.”
BackgroundMethodInfluentialVázquez-Cano, E., Mengual-Andrés, S., & López-Meneses, E. (2021) · International Journal of Educational Technology in Higher Education · doi:10.1186/s41239-021-00269-8 · Cited by 187
Conceptual Metaphors Impact Perceptions of Human-AI Collaboration
Khadpe, P., Krishna, R., Fei-Fei, L., Hancock, J. T., & Bernstein, M. S. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3415234 · Cited by 183
“osyncrasies of any particular AI system. We situate our method in goal-oriented conversational agents (or task-focused bots) as these systems represent a broad class of agents in research and product [17, 35, 55, 68, 78, 79]. 3.1 Collaborative AI task Goal-oriented AI systems, such as those for booking flights, hotel…”
BackgroundMethodInfluentialSurvey on reinforcement learning for language processing
Uc-Cetina, V., Navarro-Guerrero, N., Martin-Gonzalez, A., Weber, C., & Wermter, S. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10205-5 · Cited by 177
“2018) and M-Walk (Shum et al.”
BackgroundOptimizing Students’ Mental Health and Academic Performance: AI-Enhanced Life Crafting
Dekker, I., De Jong, E. M., Schippers, M. C., De Bruijn-Smolders, M., Alexiou, A., & Giesbers, B. (2020) · Frontiers in Psychology · doi:10.3389/fpsyg.2020.01063 · Cited by 176
Chin, H., Song, H., Baek, G., Shin, M., Jung, C., Cha, M., Choi, J., & Cha, C. (2023) · Journal of Medical Internet Research · doi:10.2196/51712 · Cited by 167
“The chatbot service that we studied is primarily intended for open-domain chat, which may not naturally provide empathetic responses [1,60].”
Robots, Artificial Intelligence, and Service Automation in Hotels
Lukanova, G., & Ilieva, G. (2019) · Robots, Artificial Intelligence, and Service Automation in Travel, Tourism and Hospitality · doi:10.1108/978-1-78756-687-320191009 · Cited by 159
AI Companions Reduce Loneliness
De Freitas, J., Oğuz-Uğuralp, Z., Uğuralp, A. K., & Puntoni, S. (2026) · Journal of Consumer Research · doi:10.1093/jcr/ucaf040 · Cited by 165
Beware of botshit: How to manage the epistemic risks of generative chatbots
Hannigan, T. R., McCarthy, I. P., & Spicer, A. (2024) · Business Horizons · doi:10.1016/j.bushor.2024.03.001 · Cited by 217
Parviainen, J., & Rantala, J. (2022) · Medicine, Health Care and Philosophy · doi:10.1007/s11019-021-10049-w · Cited by 146
Lee, C. T., Pan, L.-Y., & Hsieh, S. H. (2021) · Internet Research · doi:10.1108/intr-01-2021-0030 · Cited by 196
Technical metrics used to evaluate health care chatbots: scoping review
Abd-Alrazaq, A., Safi, Z., Alajlani, M., Warren, J., Househ, M., & Denecke, K. (2020) · Journal of Medical Internet Research · doi:10.2196/18301 · Cited by 150
“Conversational-turns per session (CPS) has been suggested as a success metric for social chatbots as exemplified by XiaoIce [85].”
MethodA Pre-Training Based Personalized Dialogue Generation Model with Persona-Sparse Data
Zheng, Y., Zhang, R., Huang, M., & Mao, X. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6518 · Cited by 219
Hsieh, S. H., & Lee, C. T. (2021) · Journal of Research in Interactive Marketing · doi:10.1108/jrim-11-2019-0179 · Cited by 169
Comparing artificial intelligence and human coaching goal attainment efficacy
Terblanche, N. H. D., Molyn, J., de Haan, E., & Nilsson, V. O. (2022) · PLoS ONE · doi:10.1371/journal.pone.0270255 · Cited by 192
“Trust • Avoid the ‘uncanny valley’ effect [37] • Communicate data privacy agreement [38] • Create consistent AI personality [39] • Reduce security and privacy concerns [40]”
BackgroundChopra, K. (2019) · International Journal of Retail & Distribution Management · doi:10.1108/ijrdm-11-2018-0251 · Cited by 208
Emotionally Intelligent Chatbots: A Systematic Literature Review
Bilquise, G., Ibrahim, S., & Shaalan, K. F. (2022) · Human Behavior and Emerging Technologies · doi:10.1155/2022/9601630 · Cited by 228
“Social chatbots are not designed to accomplish a specific task but rather to engage with humans to fulfill their need for communication and social belonging [28].”
BackgroundCombating Depression in Students using an Intelligent ChatBot: A Cognitive Behavioral Therapy
Patel, F., Thakore, R., Nandwani, I., & Bharti, S. K. (2019) · IEEE India Conference · doi:10.1109/indicon47234.2019.9030346 · Cited by 152
“Many such chatbots namely, ELIZA [2], PARRY [3], and ALICE [4], were earlier designed to pass the Turing Test [5].”
MethodThe User Experience of ChatGPT: Findings from a Questionnaire Study of Early Users
Skjuve, M. B., Følstad, A., & Brandtzæg, P. B. (2023) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3571884.3597144 · Cited by 225
“For example, whether the chatbot is perceived as empathic [25, 26] and adhering to social rules, such as turn-taking and reciprocation [27].”
BackgroundAssigning Personality/Profile to a Chatting Machine for Coherent Conversation Generation
Qian, Q., Huang, M., Zhao, H., Xu, J., & Zhu, X. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/595 · Cited by 147
“In this scenario, personality settings include age, gender, language, speaking style [Walker et al. , 1997], level of knowledge, areas of expertise, and other explicit and implicit cues that may portray character [Shum et al. , 2018] 1 .”
BackgroundAkpan, I. J., Kobara, Y. M., Owolabi, J., Akpan, A. A., & Offodile, O. F. (2024) · International Transactions in Operational Research · doi:10.1111/itor.13522 · Cited by 217
Rashid, A. B., Kausik, A. K., Al Hassan Sunny, A., & Bappy, M. H. (2023) · International Journal of Intelligent Systems · doi:10.1155/2023/8676366 · Cited by 143
The influence of chatbot humour on consumer evaluations of services
Shin, H., Bunosso, I., & Levine, L. R. (2022) · International Journal of Consumer Studies · doi:10.1111/ijcs.12849 · Cited by 171
Multi-Representation Fusion Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
Tao, C., Wu, W., Xu, C., Hu, W., Zhao, D., & Yan, R. (2019) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3289600.3290985 · Cited by 136
Tao, C., Wu, W., Xu, C., Hu, W., Zhao, D., & Yan, R. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1001 · Cited by 128
“…methods, retrieval-based methods are superior in terms of response fluency and diversity, and thus have been widely applied in commercial chatbots such as the social bot XiaoIce (Shum et al., 2018) from Microsoft, and the e-commerce assistant AliMe As-sist from Alibaba Group (Li et al., 2017a).”
MethodDesigning Personality-Adaptive Conversational Agents for Mental Health Care
Ahmad, R., Siemon, D., Gnewuch, U., & Robra-Bissantz, S. (2022) · Information Systems Frontiers · doi:10.1007/s10796-022-10254-9 · Cited by 159
“PARRY, another early example of a prototype CA developed in 1979, was designed to simulate and behave like a person with paranoid schizophrenia (Shum et al., 2018).”
BackgroundMethodInfluentialExploiting Persona Information for Diverse Generation of Conversational Responses
Song, H., Zhang, W.-N., Cui, Y., Wang, D., & Liu, T. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/721 · Cited by 145
Song, M., Zhang, H., Xing, X., & Duan, Y. (2023) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2023.103323 · Cited by 142
Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots
Yuan, C., Zhou, W., Li, M., Lv, S., Zhu, F., Han, J., & Hu, S. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1011 · Cited by 126
“Many industrial products have applied retrieval-based dialogue system, e.g., the E-commerce assistant AliMe As-sist from Alibaba Group (Li et al., 2017) and the XiaoIce (Shum et al., 2018) from Microsoft.”
Xing, X., Song, M., Duan, Y., & Mou, J. (2022) · Technology in Society · doi:10.1016/j.techsoc.2022.102049 · Cited by 133
Kim, A., & Su, Y. (2024) · System · doi:10.1016/j.system.2024.103256 · Cited by 122
Alabed, A., Javornik, A., Gregory‐Smith, D., & Casey, R. (2023) · European Journal of Marketing · doi:10.1108/ejm-01-2023-0037 · Cited by 158
Are chatbots really useful for human resource management?
Majumder, S., & Mondal, A. (2021) · International Journal of Speech Technology · doi:10.1007/s10772-021-09834-y · Cited by 186
MuTual: A Dataset for Multi-Turn Dialogue Reasoning
Cui, L., Wu, Y., Liu, S., Zhang, Y., & Zhou, M. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.130 · Cited by 110
Neural Approaches to Conversational AI
Gao, J., Galley, M., & Li, L. (2019) · now publishers, Inc. eBooks · doi:10.1561/9781680835533 · Cited by 130
FinBrain: when finance meets AI 2.0
Zheng, X., Zhu, M., Li, Q., Chen, C., & Tan, Y. (2019) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1700822 · Cited by 158
Demystifying Social Bots: On the Intelligence of Automated Social Media Actors
Assenmacher, D., Clever, L., Frischlich, L., Quandt, T., Trautmann, H., & Grimme, C. (2020) · Social Media + Society · doi:10.1177/2056305120939264 · Cited by 100
AI-Aided Teaching Model in Education 5.0
Khang, A., Muthmainnah, M., Seraj, P. M. I., Yakin, A. M. A., & Obaid, A. J. (2023) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-6684-8851-5.ch004 · Cited by 113
Liu, W., Jiang, M., Li, W., & Mou, J. (2024) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2024.123407 · Cited by 98
Kurian, N. C. (2024) · Learning Media and Technology · doi:10.1080/17439884.2024.2367052 · Cited by 159
“A well-known risk of human-chatbot interaction is the tendency for users to perceive these agents as human-like (Shum, He, and Li 2018).”
The rise of chatbots – new personal assistants in foreign language learning
Dokukina, I. V., & Gumanova, J. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.02.212 · Cited by 134
Xygkou, A., Siriaraya, P., Covaci, A., Prigerson, H. G., Neimeyer, R., Ang, C. S., & She, W.-J. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581154 · Cited by 91
“Modern advancements in conversational AI have often placed great emphasis on the development of chatbots which could talk knowledgeably in multiple domains and show emotions that are appropriate for the specific context as a means of conveying social fidelity [93], [89], [114].”
BackgroundDeng, J., & Ren, F. (2020) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2020.3034215 · Cited by 95
“vast potential applications [1], [2], such as emotional chatbots [3], emotional text-to-speech synthesizer [4], and patient emotion monitoring [5].”
BackgroundAsking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus
Liu, B., Wei, H., Niu, D., Chen, H., & He, Y. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366423.3380270 · Cited by 92
“Automatically generating question-answer pairs from unlabeled text passages is of great value to many applications, such as assisting the training of machine reading comprehension systems [10, 44, 45], generating queries/questions from documents to improve search engines [17], training chatbots to get and keep a conve…”
BackgroundConversational Information Seeking
Zamani, H., Trippas, J. R., Dalton, J., & Radlinski, F. (2023) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000081 · Cited by 233
Han, X., Zhou, M., Turner, M. J., & YEH, T. P. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445569 · Cited by 112
“Such benefits have encouraged the creation of a wide array of chatbot applications, such as virtual assistants [38], social companions [56], and interview chatbots [37].”
BackgroundDialog-to-action: conversational question answering over a large-scale knowledge base
Guo, D., Tang, D., Duan, N., Zhou, M., & Yin, J. P. (2018) · neural information processing systems · Cited by 81
Low-Resource Knowledge-Grounded Dialogue GenerationPreprint
Zhao, X., Wu, W., Tao, C., Xu, C., Zhao, D., & Yan, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.10348 · Cited by 93
“Open domain dialogue systems, due to the applications on social chatbots such as Microsoft XiaoIce (Shum et al., 2018) and virtual assistants such as Amazon Alexa (Ram et al., 2018), have drawn increasing attention from the research community of natural language processing and artificial…”
BackgroundChatbot features for anxiety and depression: a scoping review
Ahmed, A., Hassan, A., Aziz, S., Abd-alrazaq, A. A., Ali, N., Alzubaidi, M., Al-Thani, D., Elhusein, B., Siddig, M. A., Ahmed, M., et al. (2023) · Health Informatics Journal · doi:10.1177/14604582221146719 · Cited by 82
“Chatbots are computer programs that automatically communicate via text or spoken format and have been around since 1966.(13) Chatbots in mental health have been used as a means of support in training programs to level up your depression managing skills and prevention as opposed to actual therapy.”
BackgroundFramework for Design and Implementation of Chat Support System using Natural Language Processing
William, P., Lanke, G. R., Inukollu, V. N. R., Singh, P., Shrivastava, A., & Kumar, R. (2023) · International Conference on Intelligent Engineering and Management (ICIEM) · doi:10.1109/iciem59379.2023.10166939 · Cited by 82
Digital storytelling with chatbots: mapping L2 participation and perception patterns
Bailey, D., Southam, A., & Costley, J. (2021) · Interactive Technology and Smart Education · doi:10.1108/itse-08-2020-0170 · Cited by 116
Personalized Dialogue Generation with Diversified TraitsPreprint
Zheng, Y., Chen, G., Huang, M., Liu, S., & Zhu, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.09672 · Cited by 177
“Building human-like conversational systems has been a long-standing goal in artificial intelligence, where one of the major challenges is to present a consistent personality, so that the system can gain the user’s confidence and trust [39].”
BackgroundLin, R., & Lee, J.-C. (2023) · Aslib Journal of Information Management · doi:10.1108/ajim-07-2022-0337 · Cited by 115
Chaves, A. P., Egbert, J., Hocking, T. D., Doerry, E., & Gerosa, M. A. (2022) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3487193 · Cited by 113
Irfan, B., Kuoppamäki, S., Hosseini, A., & Skantze, G. (2025) · Autonomous Robots · doi:10.1007/s10514-025-10190-y · Cited by 107
Fusion of tactile and visual information in deep learning models for object recognition
Babadian, R. P., Faez, K., Amiri, M., & Falotico, E. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.11.032 · Cited by 67
Rodriguez, S., & Mune, C. D. (2022) · Reference Services Review · doi:10.1108/rsr-05-2022-0020 · Cited by 87
What makes you attached to social companion AI? A two-stage exploratory mixed-method study
Hu, D., Lan, Y., Yan, H., & Chen, C. W. (2025) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2025.102890 · Cited by 114
The Typing Cure: Experiences with Large Language Model Chatbots for Mental Health Support
Song, I., Pendse, S. R., Kumar, N., & Choudhury, M. D. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3757430 · Cited by 193
The Typing Cure: Experiences with Large Language Model Chatbots for Mental Health Support
Song, I., Pendse, S. R., Kumar, N., & De Choudhury, M. (2024) · arXiv · doi:10.48550/arxiv.2401.14362 · Cited by 64
Men, L. R., Zhou, A. Y., & Tsai, W. S. (2022) · Journal of Public Relations Research · doi:10.1080/1062726x.2022.2068553 · Cited by 92
“280) that serve as companions to satisfy users’ social and relational needs (Shum et al., 2018).”
BackgroundSocially situated artificial intelligence enables learning from human interaction
Krishna, R., Lee, D., Fei-Fei, L., & Bernstein, M. S. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2115730119 · Cited by 97
“abandon such an agent long before it crosses such a threshold (19, 20).”
BackgroundA Voice Interactive Multilingual Student Support System using IBM Watson
Ralston, K., Chen, Y., Isah, H., & Zulkernine, F. H. (2019) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2019.00309 · Cited by 72
“There are several areas of cognition that must be programmed into a chatbot in order to make it more human-like, these include empathetic conversation modelling, knowledge and memory modelling, deep neural-symbolic reasoning, and modelling and calibration of emotional or intrinsic rewards reflected in human needs [5].”
BackgroundLi, B., Yao, R., & Nan, Y. (2023) · Journal of Consumer Behaviour · doi:10.1002/cb.2218 · Cited by 74
“Social chatbots can establish an emotional connection with users by satisfying users' need for communication, affection, as well as the need to belong (Shum et al., 2018).”
Backgroundde Arriba-Pérez, F., García-Méndez, S., González-Castaño, F. J., & Costa‐Montenegro, E. (2022) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-022-03849-2 · Cited by 78
“Before virtual companions (Shum et al. 2018) become a reality, entertainment through interesting information will be more feasible.”
Hu, J., Huang, Y., Hu, X., & Xu, Y. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3205919 · Cited by 75
“Agents are usually embedded with machine learning models to detect users’ emotions from text input [9], [17], [18].”
BackgroundValidity of Chatbot Use for Mental Health Assessment: Experimental Study
Schick, A., Feine, J., Morana, S., Maedche, A., & Reininghaus, U. (2022) · JMIR mhealth and uhealth · doi:10.2196/28082 · Cited by 72
“For example, it has been shown that users may develop a strong social relationship with a chatbot when it expresses empathetic support [21,51,85,87-90].”
BackgroundSiqueira, M. A. D. S., Müller, B. C. N., & Bosse, T. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2175158 · Cited by 81
“(Ravichander & Black., 2018; Shum et al., 2018; Tsai et al., 2012) To optimally benefit from the system, its use should be comfortable and effortless.”
BackgroundLet’s Ask Again: Refine Network for Automatic Question Generation
Nema, P., Mohankumar, A. K., Khapra, M. M., Srinivasan, B. V., & Ravindran, B. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1326 · Cited by 61
“AQG is used in curating Question Answering datasets, enhancing user experience in conversational AI systems (Shum et al., 2018) and for creating educational materials (Heilman and Smith, 2010).”
MethodPani, B., Crawford, J., & Allen, K.-A. (2024) · Applications of Generative AI · doi:10.1007/978-3-031-46238-2_13 · Cited by 57
Metadata
- Authors
- Shum, H.-Y., He, X.-D., & Li, D.
- Affiliations
- Microsoft (United States) (US)
- Corresponding author
- Shum, Heung-yeung
- Venue
- Frontiers of Information Technology & Electronic Engineering
- Publisher
- Zhejiang University Press
- Published
- 2018-01
- Volume
- 19
- Issue
- 1
- Pages
- 10-26
- ISSN
- 2095-9184 (ISSN-L)
- 2095-9230
- OpenAlex
- W2964309167
- Cited by
- 749
- References
- 94
- Citations by year
- 2026: 60 · 2025: 96 · 2024: 83 · 2023: 118 · 2022: 103 · 2021: 109 · 2020: 103 · 2019: 56 · 2018: 21
- FWCI
- 40.13
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Frontiers of Information Technology & Electronic Engineering (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Microsoft Research
- Microsoft Research Asia
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Keywords
- social chatbots, Eliza, emotional connection, user engagement, emotional quotient, emotion recognition, visual awareness, dialogue systems, human-AI interaction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.