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
Items 101–200 of 746
Sun, G., Zhan, X., & Such, J. (2024) · ACM Conversational User Interfaces 2024 · doi:10.1145/3640794.3665887 · Cited by 55
Zeng, Z., He, K., Yan, Y., Liu, Z., Wu, Y., Xu, H., Jiang, H., & Xu, W. (2021) · doi:10.18653/v1/2021.acl-short.110 · Cited by 86
“Detecting Out-of-Domain (OOD) or unknown in-tents from user queries is an essential component in a task-oriented dialog system (Gnewuch et al., 2017; Akasaki and Kaji, 2017; Tulshan and Dhage, 2018; Shum et al., 2018).”
BackgroundTa-Johnson, V. P., Boatfield, C., Wang, X., DeCero, E., Krupica, I. C., Rasof, S. D., Motzer, A., & Pedryc, W. M. (2022) · JMIR Human Factors · doi:10.2196/38876 · Cited by 51
“Because they are made to be virtual companions to users, social chatbots are created to embody human-like personalities, emotions, and behavior and facilitate social interactions catering to the individual needs of the user [2,16].”
BackgroundAi Chatbots: Transforming the Digital World
Paliwal, S., Bharti, V., & Mishra, A. K. (2019) · Intelligent systems reference library · doi:10.1007/978-3-030-32644-9_34 · Cited by 57
Lee, J. H., Yang, H., Shin, D., & Kim, H. (2020) · ELT Journal · doi:10.1093/elt/ccaa035 · Cited by 51
Yang, T., & Chen, J. (2022) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2022.100119 · Cited by 76
Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue
Liu, L., Zhang, Z., Zhao, H., Zhou, X., & Zhou, X. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i15.17582 · Cited by 52
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
Sun, H., Xu, G., Deng, J., Cheng, J., Zheng, C., Zhou, H., Peng, N., Zhu, X., & Huang, M. (2022) · Findings of the Association for Computational Linguistics: ACL 2022 · doi:10.18653/v1/2022.findings-acl.308 · Cited by 49
Chin, H., Lima, G., Shin, M., Zhunis, A., Cha, C., Choi, J., & Cha, M. (2023) · Journal of Medical Internet Research · doi:10.2196/40922 · Cited by 49
“Such matching can be regarded as the simplest form of predicting user intent and conversation context [6].”
BackgroundOn the relationship between mind perception and social support of chatbots
Lee, I., & Hahn, S. (2024) · Frontiers in Psychology · doi:10.3389/fpsyg.2024.1282036 · Cited by 71
“Social chatbots, or chatbots that perform social functions, are designed to provide users with social support while having daily conversations and building social relationships with them (Shum et al., 2018; Ta et al., 2020).”
BackgroundZand, A., Sharma, A., Stokes, Z., Reynolds, C., Montilla, A., Sauk, J., & Hommes, D. (2020) · Journal of Medical Internet Research · doi:10.2196/15589 · Cited by 48
“For instance, Artificial Linguistic Internet Computer Entity and ELIZA, two classic chatbots, utilize hand-constructed databases to generate a response that matches a given human input [20].”
BackgroundQuestion-type Driven Question Generation
Zhou, W., Zhang, M., & Wu, Y. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1622 · Cited by 49
“Question generation (QG) can be effectively applied to many fields, including question answering (Duan et al., 2017), dialogue system (Shum et al., 2018) and education.”
BackgroundLive support by chatbots with artificial intelligence: A future research agenda
Camilleri, M. A., & Troise, C. (2022) · Service Business · doi:10.1007/s11628-022-00513-9 · Cited by 63
“Alternatively, they use them to scrutinize their personal data (Shum et al. 2018).”
BackgroundYim, M. C. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2234114 · Cited by 59
“Extensive discussions have focused on incorporating emotional cues into chatbot design through the choice of language (Chaves & Gerosa, 2021; Ho et al., 2018; Shum et al., 2018).”
Kopp, S., & Krämer, N. (2021) · Frontiers in Psychology · doi:10.3389/fpsyg.2021.580955 · Cited by 47
“…only respond to users’ specific questions or commands in natural language (spoken or typed), but also to establish a connection by tracking the user’s emotional state (Li et al., 2018) and satisfying users’ social needs for communication, affection, entertainment, or belonging (Shum et al., 2018).”
BackgroundLearning towards conversational AI: A survey
Fu, T., Gao, S., Zhao, X., Wen, J.-R., & Yan, R. (2022) · AI Open · doi:10.1016/j.aiopen.2022.02.001 · Cited by 46
“Originated from the ELIZA (Shum et al., 2018) in the last century, open-domain conversation is a fascinating and exciting topic that continues to pique the curiosity of scholars.”
BackgroundLearning Neural Templates for Recommender Dialogue System
Liang, Z., Hu, H., Xu, C., Miao, J., He, Y., Chen, Y., Geng, X., Liang, F., & Jiang, D. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.617 · Cited by 54
“Besides, the social bots such as Xi-aoIce (Shum et al., 2018) and PersonaChat (Zhang et al., 2018a) also exhibit the great potential on the emotional companion to humans.”
Rese, A., & Tränkner, P. (2023) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2023.102699 · Cited by 70
Coherent Comments Generation for Chinese Articles with a Graph-to-Sequence Model
Li, W., Xu, J., He, Y., Yan, S., Wu, Y., & Sun, X. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1479 · Cited by 60
“The ability to automatically generate comments is desirable for online news platforms, especially comments that can encourage user engagement and interactions, serving as one form of intelligent chatbot (Shum et al., 2018).”
BackgroundChan, Z., Li, J., Yang, X., Chen, X., Hu, W., Zhao, D., & Yan, R. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1201 · Cited by 52
“Over the past decade, a myriad of conversational systems have been proposed in the field of artifi-cial intelligence and achieved remarkable success in various industry scenarios, such as e-commerce assistant (Li et al., 2017) and chit-chat machine XiaoIce (Shum et al., 2018).”
BackgroundDesirable or Distasteful? Exploring Uncertainty in Human-Chatbot Relationships
Pan, S., Cui, J., & Mou, Y. (2024) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2023.2256554 · Cited by 44
“Users are expected to build emotional connections and intimate relationships with social chatbots through simulated affective communication (Shum et al., 2018).”
Xygkou, A., Siriaraya, P., She, W. J., Covaci, A., & Ang, C. S. (2024) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2292880 · Cited by 61
“In the near future, it is not inconceivable for chatbots to play a more important role in therapies, training, or to simply provide social companionship (Fiske et al., 2019; Fitzpatrick et al., 2017; Shum et al., 2018; Winkler & S € o Llner, 2018).”
Deceptive AI Ecosystems: The Case of ChatGPT
Zhan, X., Xu, Y., & Sarkadi, S. (2023) · Proceedings of the 5th International Conference on Conversational User Interfaces · doi:10.1145/3571884.3603754 · Cited by 43
“These systems were limited in their reliance on pattern-matching algorithms and linguistic rules,and progress was minimal [2, 17, 64].”
BackgroundDevelopment of an E-Commerce Chatbot for a University Shopping Mall
Oguntosin, V., & Olomo, A. (2021) · Applied Computational Intelligence and Soft Computing · doi:10.1155/2021/6630326 · Cited by 49
“…personal assistant Siri by Apple in 2011 and then Cortana by Microsoft and more recently social chatbots such as Microsoft’s Xiaoice in the current social media age, the scope of chatbots as conversational systems has been extended to cover a wide range of domains including e-commerce [12, 16].”
BackgroundMethodDigital Mental Health: Role of Artificial Intelligence in Psychotherapy
Bhatt, S. (2024) · Annals of Neurosciences · doi:10.1177/09727531231221612 · Cited by 52
Deep context modeling for multi-turn response selection in dialogue systems
Li, L., Li, C., & Ji, D. (2020) · Information Processing & Management · doi:10.1016/j.ipm.2020.102415 · Cited by 46
Multi-hop Question Generation with Graph Convolutional Network
Su, D., Xu, Y., Dai, W., Ji, Z., Yu, T., & Fung, P. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.416 · Cited by 59
Multi-task learning with graph attention networks for multi-domain task-oriented dialogue systems
Zhao, M., Wang, L., Jiang, Z., Li, R., Lu, X., & Hu, Z. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110069 · Cited by 40
Using AI Chatbots in Education: Recent Advances Challenges and Use Case
Aleedy, M., Atwell, E., & Meshoul, S. (2022) · Algorithms for intelligent systems · doi:10.1007/978-981-19-1653-3_50 · Cited by 56
Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
Roller, S., Boureau, Y.-L., Weston, J., Bordes, A., Dinan, E., Fan, A., Gunning, D., Ju, D., Li, M., Poff, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.12442 · Cited by 38
“tral captions, with a win rate of 64.5% (Shuster et al., 2018). While some developers have chosen to use fixed personalities in their bots, such as Xiaoice, which has the personality of a young woman (Shum, He, and Li, 2018; Zhou et al., 2020), we believe it is better for a bot to be able to adapt a multitude of person…”
BackgroundInfluentialHuang, Y., & Gursoy, D. (2024) · International Journal of Contemporary Hospitality Management · doi:10.1108/ijchm-11-2023-1800 · Cited by 36
How does anthropomorphism promote consumer responses to social chatbots: mind perception perspective
Li, B., Yao, R., & Nan, Y. (2025) · Internet Research · doi:10.1108/intr-04-2024-0583 · Cited by 36
A survey on construction and enhancement methods in service chatbots design
Peng, Z., & Ma, X. (2019) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-019-00012-3 · Cited by 45
“2, modular task-oriented dialog system mainly consists of three components (Shum et al. 2018): 1.”
BackgroundInvestigation on Works and Military Applications of Artificial Intelligence
Wang, W., Liu, H., Lin, W., Chen, Y., & Yang, J. (2020) · IEEE Access · doi:10.1109/access.2020.3009840 · Cited by 39
“Social chatbots such as Apple’s Siri [15] and Microsoft’s XiaoIce [16] and Cortana [17] have both an intellectual quotient (IQ) and emotional quotient (EQ), similar to human beings.”
BackgroundKnowledge-Grounded Dialogue Flow Management for Social Robots and Conversational Agents
Grassi, L., Recchiuto, C. T., & Sgorbissa, A. (2022) · International Journal of Social Robotics · doi:10.1007/s12369-022-00868-z · Cited by 49
“As stated in [38], early conversational systems such as Eliza [39], Parry [40],”
BackgroundPetsolari, M., Ibrahim, S. B., & Slovak, P. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642619 · Cited by 35
“This builds on prior work that has considered agent roles and how people are motivated to use these technologies, and what people perceive about the tech-nology’s expertise and intelligence [253, 321, 347].”
Mauriello, M. L., Tantivasadakarn, N., Mora-Mendoza, M. A., Lincoln, E. T., Hon, G., Nowruzi, P., Simon, D., Hansen, L., Goenawan, N. H., Kim, J., et al. (2021) · JMIR Formative Research · doi:10.2196/25294 · Cited by 45
“Research into improving conversational systems spans a number of domains such as customer service [7,8], companionship [9,10], and, increasingly, mental health [11-14].”
BackgroundMove fast and break people? Ethics, companion apps, and the case of Character.ai
Bakir, V., & McStay, A. (2025) · AI & Society · doi:10.1007/s00146-025-02408-5 · Cited by 68
The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection
Lin, Z., Cai, D., Wang, Y., Liu, X., Zheng, H.-T., & Shi, S. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.741 · Cited by 42
“Building intelligent conversation systems (Shum et al., 2018; Kollar et al., 2018) is gaining more and more attention in recent years.”
Background“I’m Here for You”: Can Social Chatbots Truly Support Their Users? A Literature Review
van Wezel, M. M. C., Croes, E. A. J., & Antheunis, M. L. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68288-0_7 · Cited by 53
An Ontology-Based Chatbot to Enhance Experiential Learning in a Cultural Heritage Scenario
Casillo, M., Santo, M. D., Mosca, R., & Santaniello, D. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.808281 · Cited by 46
“…Pattern Matching (Suhaili et al., 2021), Parsing (Adamopoulou and Moussiades, 2020), Markov Chain Models (Lokman and Jasni, 2010), Semantic Nets (Shum et al., 2018), AIML (Adikari et al., 2019), Structured Query Language (SQL), and Relational Database Language Tricks (Augello et al., 2009;…”
Neural Response Generation with Meta-words
Xu, C., Wu, W., Tao, C., Huang, H., Schuerman, M., & Wang, Y. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1538 · Cited by 40
“Recently, building a chatbot for open domain conversation (Vinyals and Le, 2015) has attracted increasing attention, not only owing to the availability of large amount of human-human conversation data on internet, but also because of the success of such systems in real products such as the social bot XiaoIce (Shum et…”
BackgroundSavastano, M., Biclesanu, I., Anagnoste, S., Laviola, F. A., & Cucari, N. (2024) · Management Decision · doi:10.1108/md-10-2023-1967 · Cited by 48
Pop Music Generation: From Melody to Multi-style Arrangement
Zhu, H., Liu, Q., Yuan, N. J., Zhang, K., Zhou, G., & Chen, E. (2020) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3374915 · Cited by 47
“Motivated by [35, 50], we propose a new MSMICA , to control the style of the generated music.”
BackgroundInfluentialDialogue Response Selection with Hierarchical Curriculum Learning
Su, Y., Cai, D., Zhou, Q. S., Lin, Z., Baker, S., Cao, Y., Shi, S., Collier, N., & Wang, Y. (2021) · doi:10.18653/v1/2021.acl-long.137 · Cited by 43
“Building intelligent conversation systems is a longstanding goal of artificial intelligence and has attracted much attention in recent years (Shum et al., 2018; Kollar et al., 2018).”
BackgroundEbner, P., & Szczuka, J. (2025) · arXiv · doi:10.48550/arxiv.2503.00195 · Cited by 33
Croes, E. A. J., Antheunis, M. L., Goudbeek, M. B., & Wildman, N. (2022) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2022.2075574 · Cited by 52
“These commercial chatbots typically operate within restricted domains with well-defined schemas (Shum et al., 2018), e.g., addressing targeted questions about highly specific topics.”
BackgroundInfluentialMalik, M. A., Amjad, A. I., Aslam, S., & Fakhrou, A. A. (2024) · Frontiers in Research Metrics and Analytics · doi:10.3389/frma.2024.1486832 · Cited by 78
Controllable Open-ended Question Generation with A New Question Type Ontology
Cao, S., & Wang, L. (2021) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2021.acl-long.502 · Cited by 67
“Questions generated by our model have diverse T YPE s. et al., 2019) and building open-domain dialogue systems (Shum et al., 2018).”
Evaluation Metrics for Health Chatbots: A Delphi Study
Denecke, K., Abd-Alrazaq, A. A., Househ, M. S., & Warren, J. (2021) · Methods of Information in Medicine · doi:10.1055/s-0041-1736664 · Cited by 32
An Empathetic AI for Mental Health Intervention: Conceptualizing and Examining Artificial Empathy
Shao, R. (2023) · doi:10.1145/3588967.3588971 · Cited by 31
ComPeer: A Generative Conversational Agent for Proactive Peer Support
Liu, T., Zhao, H., Liu, Y., Wang, X., & Peng, Z. (2024) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3654777.3676430 · Cited by 77
Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots
Wu, Y., Wu, W., Li, Z., & Zhou, M. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-2067 · Cited by 33
“…because retrieval-based methods can return fluent and informative responses, but also because they have been successfully applied to many real products such as the social-bot XiaoIce from Microsoft ( Shum et al., 2018) and the E-commerce assistant AliMe Assist from Alibaba Group (Li et al., 2017).”
MethodInfluentialDistilling Knowledge for Fast Retrieval-based Chat-bots
Tahami, A. V., Ghajar, K., & Shakery, A. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401296 · Cited by 32
“They have been used in real-world products such as Microsoft XiaoIce [15] and Alibaba GroupâĂŹs AliMe Assist [9].”
MethodImage Inspired Poetry Generation in XiaoIcePreprint
Cheng, W., Wu, C.-C., Song, R., Fu, J., Xie, X., & Nie, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.03090 · Cited by 38
Perceived authenticity of virtual characters makes the difference
Huang, J., & Jung, Y. (2022) · Frontiers in Virtual Reality · doi:10.3389/frvir.2022.1033709 · Cited by 40
“In conventional HCI research, “ realness ” is often regarded as equal to “ human-likeness, ” which mainly concerns whether a machine looks and feels like an actual human to users (Turing, 1950; Weizenbaum, 1966; de Borst and de Gelder, 2015; Shum et al., 2018; Chaves and Gerosa, 2019).”
BackgroundInfluentialAbedi, M., Alshybani, I., Shahadat, M., & Murillo, M. S. (2023) · Qeios · doi:10.32388/md04b0 · Cited by 68
“This intellectual query led to the creation of ELIZA in the 1960s by Joseph Weizenbaum [84–86] (the first purple node on the upper layer in Figure 2).”
BackgroundChatbots Development Using Natural Language Processing: A Review
Abdulla, H. M. D., Eltahir, A. M., Alwahaishi, S., Saghair, K., Platoš, J., & Snåšel, V. (2022) · International Conference on Circuits, Systems, Communications and Computers (CSCC) · doi:10.1109/cscc55931.2022.00030 · Cited by 39
“[8].”
MethodProactive behavior in voice assistants: A systematic review and conceptual model
Bérubé, C., Nißen, M., Vinay, R., Geiger, A., Budig, T., Bhandari, A., Benito, C. R. P., Ibarcena, N., Pistolese, O., Li, P., et al. (2024) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2024.100411 · Cited by 58
Multi-Task Learning with Language Modeling for Question Generation
Zhou, W., Zhang, M., & Wu, Y. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1337 · Cited by 36
“…questions to boost the question answering systems (Duan et al., 2017; Tang et al., 2017); (2) QG enables the dialogue systems to ask questions which make it more proactive (Shum et al., 2018; Colby, 1975); (3) QG can help to generate questions for reading comprehension texts in the education field.”
Enhanced Speaker-Aware Multi-Party Multi-Turn Dialogue Comprehension
Ma, X., Zhang, Z., & Zhao, H. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3284516 · Cited by 40
“…machines to read dialogue contexts and make response (Reddy, Chen, and Manning 2019; Choi et al. 2018; Sun et al. 2019; Cui et al. 2020), whose common application is building intelligent human-computer interactive systems (Chen et al. 2017a; Shum, He, and Li 2018; Li et al. 2017; Zhu et al. 2018).”
BackgroundYuan, J., Peng, X., Liu, Y. H., & Wang, Q. (2024) · Computers in Human Behavior · doi:10.1016/j.chb.2024.108501 · Cited by 33
Hua, K., Feng, Z., Tao, C., Yan, R., & Zhang, L. (2020) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3340531.3411967 · Cited by 34
“…first group is retrieval-based dialogue systems [9, 32, 38, 40, 52] which select the proper response from the response candidates under the given user input or dialogue context, and have been applied in many industrial products such as XiaoIce from Microsoft [29] and AliMe Assist from Alibaba [14].”
MethodFeng, J., Tao, C., Wu, W., Feng, Y., Zhao, D., & Yan, R. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1370 · Cited by 30
“ered some real products such as the social bot XiaoIce from Microsoft (Shum et al., 2018), and the E-commerce assistant AliMe Assist from Alibaba Group (Li et al.”
BackgroundOffline and Online Satisfaction Prediction in Open-Domain Conversational Systems
Choi, J. I., Ahmadvand, A., & Agichtein, E. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3358047 · Cited by 40
“Incorporating artificial personalities are studied to improve empathetic, personalized engagements within these systems [10, 30].”
BackgroundChat with Bots Intelligently: A Critical Review & Analysis
Dsouza, R., Sahu, S., Patil, R., & Kalbande, D. R. (2019) · 2019 International Conference on Advances in Computing, Communication and Control (ICAC3) · doi:10.1109/icac347590.2019.9036844 · Cited by 27
“It incorporated Rogerian Psychotherapy for conversations[19].”
Background36 Questions to Loving a Chatbot: Are People Willing to Self-disclose to a Chatbot?
Croes, E. A. J., & Antheunis, M. L. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68288-0_6 · Cited by 36
“Social chatbots attempt to connect with their users by asking questions, gathering information and keeping the conversation going so that people want to keep interacting with the chatbot [16].”
BackgroundLearning Implicit User Profile for Personalized Retrieval-Based Chatbot
Qian, H., Dou, Z., Zhu, Y., Ma, Y., & Wen, J.-R. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482269 · Cited by 49
“Inconsistent personality is one of the most mentioned challenges of current open-domain chatbots [7, 35].”
BackgroundTowards Automatic Job Description Generation with Capability-Aware Neural Networks
Qin, C., Yao, K., Zhu, H., Xu, T., Shen, D., Chen, E., & Xiong, H. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3145396 · Cited by 35
“A motivating example of writing job description. and chatbot [21], [22].”
BackgroundArabic chatbot technologies: A scoping review
Ahmed, A., Ali, N., Alzubaidi, M. S., Zaghouani, W., Abd-Alrazaq, A. A., & Househ, M. S. (2022) · Computer Methods and Programs in Biomedicine Update · doi:10.1016/j.cmpbup.2022.100057 · Cited by 27
Zhou, A. Y., Tsai, W. S., & Men, L. R. (2024) · International Journal of Business Communication · doi:10.1177/23294884241229223 · Cited by 43
“…which “present themselves as humanlike, with personality and appropriate emotions” (Croes & Antheunis, 2021, p. 280) that can satisfy users’ social needs (Shum et al., 2018; Zhou et al., 2023) and facilitate brands’ relational efforts (L. Lu et al., 2022; Men et al., 2022; Youn & Jin, 2021).”
Learning to Memorize Entailment and Discourse Relations for Persona-Consistent Dialogues
Chen, R., Wang, J., Yu, L.-C., & Zhang, X. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26489 · Cited by 49
Thunström, A. O., Carlsen, H. K., Ali, L., Larson, T., Hellström, A., & Steingrímsson, S. (2024) · JMIR Human Factors · doi:10.2196/54581 · Cited by 33
“Nonetheless, there is research that suggests the design flaws in a chatbot system can markedly diminish its effectiveness, potentially leading to perceptions of unhelpfulness among users [3].”
BackgroundMethodInfluentialPerioperative application of chatbots: a systematic review and meta-analysis
Lin, S.-J., Sun, C., Chen, D., Kang, Y., Lai, N. M., Chen, K., & Chen, C. (2024) · BMJ Health & Care Informatics · doi:10.1136/bmjhci-2023-100985 · Cited by 39
Smooth Talking: Generative Versus Scripted Coaching Chatbot Adoption and Efficacy Comparison
Terblanche, N. H. D. (2024) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2024.2423125 · Cited by 35
“Building on the need for social adept-ness in chatbots, Shum et al. (2018) argue for the integration of empathy, social skills, personality, and a balance of emotional and intellectual understanding (EQ and IQ).”
Jung, Y. M., & Jo, H. (2025) · Sustainability · doi:10.3390/su17136082 · Cited by 48
Read, Attend and Comment: A Deep Architecture for Automatic News Comment Generation
Yang, Z., Xu, C., Wu, W., & Li, Z. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1512 · Cited by 39
“In our intended target use, we explicitly disclose the generated comments on news as being formulated automatically by an entertaining and engaging chatbot (Shum et al., 2018).”
BackgroundAdversarial Self-Supervised Learning for Out-of-Domain Detection
Zeng, Z., He, K., Yan, Y., Xu, H., & Xu, W. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.447 · Cited by 37
“Task-oriented dialog systems (Sarikaya, 2017; Akasaki and Kaji, 2017; Gnewuch et al., 2017; Shum et al., 2018; Tulshan and Dhage, 2018) such as Google’s DialogFlow or Amazon’s Lex have become ubiquitous to make people interact with machines using natural language.”
BackgroundStructural Pre-training for Dialogue Comprehension
Zhang, Z., & Zhao, H. (2021) · doi:10.18653/v1/2021.acl-long.399 · Cited by 36
“…response selection (Lowe et al., 2015; Wu et al., 2017; Zhang et al., 2018) and answering questions (Sun et al., 2019a; Cui et al., 2020), whose common application is building intelligent human-computer interactive systems (Chen et al., 2017a; Shum et al., 2018; Li et al., 2017; Zhu et al., 2018b).”
Background(2020) · Pacific Asia journal of the Association for Information Systems · doi:10.17705/1pais.12201 · Cited by 26
Transparency Enhances Positive Perceptions of Social Artificial Intelligence
Xu, Y., Bradford, N., & Garg, R. (2023) · Human Behavior and Emerging Technologies · doi:10.1155/2023/5550418 · Cited by 42
“[4], social chatbots “take time to converse like a human, present results, offering perspectives, prompting new topics to keep the conversation going” (p.”
BackgroundAutomatic Article Commenting: the Task and Dataset
Qin, L., Liu, L., Bi, W., Wang, Y., Liu, X., Hu, Z., Zhao, H., & Shi, S. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-2025 · Cited by 38
“…interest in natural language generation tasks, such as machine translation (Brown et al., 1990; Bahdanau et al., 2014), dialog (Williams and Young, 2007; Shum et al., 2018), text manipulation (Hu et al., 2017), visual description generation (Vinyals et al., 2015; Liang et al., 2017), and so forth.”
Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Data
Zhang, R., Zheng, Y., Shao, J., Mao, X., Xi, Y., & Huang, M. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.277 · Cited by 31
The Role of Chatbots in End-To-End Intelligent Automation and Future Employment Dynamics
Anagnoste, S., Biclesanu, I., D’Ascenzo, F., & Savastano, M. (2021) · Springer proceedings in business and economics · doi:10.1007/978-3-030-59972-0_20 · Cited by 36
DisBot: A Portuguese Disaster Support Dynamic Knowledge Chatbot
Boné, J., Ferreira, J. C., Ribeiro, R., & Cadete, G. (2020) · Applied Sciences · doi:10.3390/app10249082 · Cited by 24
“These entities have, nevertheless, the tremendously challenging task of efficiently working in open domain scenarios [7].”
InfluentialDialogue History Matters! Personalized Response Selection in Multi-Turn Retrieval-Based Chatbots
Li, J., Liu, C., Tao, C., Chan, Z., Zhao, D., Zhang, M., & Yan, R. (2021) · ACM Transactions on Information Systems · doi:10.1145/3453183 · Cited by 49
“Dialogue systems have received a considerable amount of attention from academic researchers and have achieved remarkable success in a myriad of industry scenarios, such as in chit-chat machines [46], information seeking and searching [1, 12], and intelligent assistants [22].”
BackgroundMy Virtual Colleague: A State-of-the-Art Analysis of Conversational Agents for the Workplace
Feng, S., & Buxmann, P. (2020) · Hawaii International Conference on System Sciences (HICSS) · doi:10.24251/hicss.2020.020 · Cited by 29
“IPAs like Siri1 and Google Assistant2 can perform a large range of simple actions, most of which are completed with very few CPS with the goal to minimize this number.”
BackgroundInfluentialEnhancements to the Sequence-to-Sequence-Based Natural Answer Generation Models
Palasundram, K., Sharef, N. M., Kasmiran, K. A., & Azman, A. (2020) · IEEE Access · doi:10.1109/access.2020.2978551 · Cited by 29
“In 1966, a chatbot called ‘‘ELIZA’’ was developed to study the natural language communication between man and machine [5]–[7].”
BackgroundRecommending Moodle Resources Using Chatbots
Souali, K., Rahmaoui, O., Ouzzif, M., & Haddioui, I. E. (2019) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis.2019.00110 · Cited by 23
“They should be able to communicate through different modalities, suggest or encourage new topics to extend the conversation further and need to develop empathy, social skills, and personality to gain users’ confidence and trust [10] .”
BackgroundInfluentialMultimodal sentiment and emotion recognition in hyperbolic space
Araño, K. A., Orsenigo, C., Soto, M., & Vercellis, C. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115507 · Cited by 32
Israfilzade, K. (2021) · JOURNAL OF LIFE ECONOMICS · doi:10.15637/jlecon.8.4.12 · Cited by 23
Multi-Turn Dialogue Reading Comprehension With Pivot Turns and Knowledge
Zhang, Z., Li, J., & Zhao, H. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3058616 · Cited by 31
“MULTI-TURN dialogue reading comprehension aims to teach machines to read dialogue contexts and solve tasks such as response selection [26], [44], [54] and answering questions [35], whose common application is building intelligent human-computer interactive systems [3], [18], [33], [62].”
BackgroundThompson, D., & Baranowski, T. (2019) · Translational Behavioral Medicine · doi:10.1093/tbm/ibz065 · Cited by 22
Using Artificial Intelligence (AI) in Developing Marketing Strategies
Mirwan, S. H., Ginny, P. L., Darwin, D., Ghazali, R., & Lenas, M. N. J. (2023) · International Journal of Applied Research and Sustainable Sciences · doi:10.59890/ijarss.v1i3.896 · Cited by 48
“By using NLP (Natural Language Processing), chatbots can understand and respond to human language in a natural way(Shum et al., 2018).”
MethodOpen Domain Dialogue Generation with Latent Images
Yang, Z., Wu, W., Hu, H., Xu, C., Wang, W., & Li, Z. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i16.17675 · Cited by 35
Profile Consistency Identification for Open-domain Dialogue Agents
Song, H., Wang, Y., Zhang, W., Zhao, Z., Liu, T., & Liu, X. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.539 · Cited by 37
“This format is widely applied in real-world dialogue systems, such as Bowden et al. (2017), Shum et al. (2018), and Pichl et al. (2018).”
BackgroundValue propositions of chatbots to support innovation management processes
Johannsen, F., Schaller, D., & Klus, M. F. (2020) · Information Systems and e-Business Management · doi:10.1007/s10257-020-00487-z · Cited by 32
“More, an IR-chatbot of an airline could be used to retrieve information from a flight database as an example (e.g., Makhalova et al. 2019; Shum et al. 2018).”
MethodChatbot for Online Customer Service: Customer Engagement in the Era of Artificial Intelligence
Ho, R. C. (2021) · Advances in e-business research series · doi:10.4018/978-1-7998-7603-8.ch002 · Cited by 42
Zhao, H., & Min, Q. (2024) · Information & Management · doi:10.1016/j.im.2024.104012 · Cited by 29
Chatting with chatbots: Sign making in text-based human–computer interaction
Duncker, D. (2020) · Sign Systems Studies · doi:10.12697/sss.2020.48.1.05 · Cited by 23
““The primary goal of social chatbots is to be AI companions to humans with an emotional connection” (Shum et al. 2018: 14).”
Background
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.