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 301–400 of 746
Chatbots in Pharmacy: A Boon or a Bane for Patient Care and Pharmacy Practice?
Ramadhani, C. (2023) · Sciences of Pharmacy · doi:10.58920/sciphar02030001 · Cited by 21
“This limitation arises because chatbots rely on predefined rules or machine learning algorithms that have a limited scope of knowledge and understanding (96).”
BackgroundGuo, J., Tao, D., & Yang, C. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-981-13-8779-1_79 · Cited by 12
A framework to co-optimize task and social dialogue policies using Reinforcement Learning
Pécune, F., Marsella, S., & Jain, A. (2020) · ACM International Conference on Intelligent Virtual Agents (IVA) · doi:10.1145/3383652.3423877 · Cited by 16
“A similar dichotomy in terms of conversational goals exists in human-computer interactions [24].”
BackgroundJoshi, R., & Bengler, K. J. (2024) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3687272.3688297 · Cited by 16
“CAs were designed to imitate human behavior based on manually defined rules [54].”
The Three Social Dimensions of Chatbot Technology
Figueroa-Torres, M. (2024) · Philosophy & Technology · doi:10.1007/s13347-024-00826-9 · Cited by 17
“Frequently, while not exclusively, termed social chatbots in computer science literature (Gao et al., 2019; Shum et al., 2018), or Social AI (Sætra, 2020), these systems are crafted to satisfy emotional needs rather than functional tasks 1 such as customer service or assistance.”
Artificial intelligence and the future of otherness: what kind of other can an AI be for a human?
Fernandez‐Borsot, G. (2025) · AI & Society · doi:10.1007/s00146-025-02281-2 · Cited by 17
“…in how conversational agents (AIs able to hold conversations with humans, abbreviated CAs) adapt to user preferences and settings (see, for example, Shum, He, and Li 2018) and how designers easily tend to make them sycophantic (Perez et al. 2022; Turpin et al. 2023), and accommodating (Dinan et…”
Chen, B., Wen, R., Tan, S., & Li, Y. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3720067 · Cited by 18
Improving Neural Question Generation using Deep Linguistic Representation
Yuan, W., He, T., & Dai, X. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3449975 · Cited by 10
“It is also useful for actively gathering users’ feedback in AI conversational systems [45] and for generating educational materials [16].”
BackgroundFcl-Taco2: Towards Fast, Controllable and Lightweight Text-to-Speech Synthesis
Wang, D., Deng, L., Zhang, Y., Zheng, N., Yeung, Y. T., Chen, X. D., Liu, X., & Meng, H. M. L. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414870 · Cited by 12
“As a key component of speech communication technologies, TTS has been widely applied in human-computer interaction including virtual assistants and chatbots [1].”
BackgroundFarah, J. C., Sharma, V., Ingram, S., & Gillet, D. (2021) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3472307.3484677 · Cited by 14
“To inform the study of this potential new use case, we built on the design of chatbots equipped with humor capabilities [17, 45],”
MethodLarge Language Models: AI's Legal Revolution
Bent, A. A. (2023) · Pace law review · doi:10.58948/2331-3528.2083 · Cited by 13
A Human–Machine Interaction Scheme Based on Background Knowledge in 6G-Enabled IoT Environment
Yuan, Y., & Cai, X. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3050880 · Cited by 10
Conversational Query Rewriting with Self-Supervised Learning
Liu, H., Chen, M., Wu, Y., He, X., & Zhou, B. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413557 · Cited by 14
“Building conversational bots has attracted increasing attention due to the promising potentials on applications like virtual assistants [1] or customer service systems [2].”
BackgroundSelf-citationTowards User-Centric Text-to-Text Generation: A Survey
Yang, D., & Flek, L. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-83527-9_1 · Cited by 10
SEPRG: Sentiment aware Emotion controlled Personalized Response Generation
Firdaus, M., Jain, U., Ekbal, A., & Bhattacharyya, P. (2021) · International Conference on Natural Language Generation · doi:10.18653/v1/2021.inlg-1.39 · Cited by 20
“This helps to make the dialogue engaging and also makes it easier to build trust and credibility with the users (Shum et al., 2018).”
BackgroundThe role of chatterbots in enhancing tourism: a case study of Penang tourism spots
Kasinathan, V., Mustapha, A., Rani, M. F. C. A., & Mostafa, S. A. (2020) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v9.i4.pp569-575 · Cited by 10
“It has been demonstrated that evaluating chatterbots using this method is one of the most effective ways to compare to other chatterbots competing for ISSN: 2252-8938 Int J Artif Intell, Vol. 9, No. 4, December 2020: 569 – 575 570 the Loebner Prize [6] as the maxims provide a scoring matrix, where every chatterbot is…”
BackgroundAugmenting Conversational Agents with Ambient Acoustic Contexts
Park, C., Min, C., Bhattacharya, S., & Kawsar, F. (2020) · International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) · doi:10.1145/3379503.3403535 · Cited by 13
“bots [18, 37, 45] focus on retrieving and understanding various contexts from text-based conversations.”
BackgroundEmploying chatbots for data collection in participatory journalism and crisis situations
Veglis, A. A., & Kotenidis, E. (2021) · Journal of Applied Journalism & Media Studies · doi:10.1386/ajms_00044_1 · Cited by 13
A Survey of Document Grounded Dialogue Systems (DGDS)Preprint
Ma, L., Zhang, W., Li, M., & Liu, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.13818 · Cited by 23
“Shum et al. [93] outlined the advantages and disadvantages of the current social chatbots.”
BackgroundChat as Expected: Learning to Manipulate Black-box Neural Dialogue ModelsPreprint
Liu, H., Wang, Z., Derr, T., & Tang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.13170 · Cited by 13
“From early such as chatbots ELIZA (Weizenbaum, 1966) and ALICE (Wallace, 2001) to later ones like Siri and XiaoIce (Shum et al., 2018), the techniques have evolved from hand-crafted rule-based meth-ods (Weizenbaum, 1966; Goddeau et al., 1996), retrieval-based methods (Lu and Li, 2013; Hu et al., 2014) to learning-base…”
Manipulation and the Ai Act: Large Language Model Chatbots and the Danger of MirrorsPreprint
Krook, J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4719835 · Cited by 23
A survey of autonomous monitoring systems in mental health
Gopalakrishnan, A., Gururajan, R., Zhou, X., Venkataraman, R., Chan, K. C., & Higgins, N. (2024) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1527 · Cited by 18
“The user can communicate with the chatbot using open-ended text or multiple-choice questions (Shum et al., 2018).”
Method(2024) · Journal of Logistics Informatics and Service Science · doi:10.33168/jliss.2024.0730 · Cited by 19
Is more human-like better? The impact of virtual streamer language naturalness on user engagement
Zhang, R., Fang, J., Han, L., & Liao, M. (2025) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2025.124392 · Cited by 11
Safshekan, M., Feili, A., Shojaeifard, A., & Sorooshian, S. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1718244 · Cited by 27
“A chat robot can interact with a person and independently answer their questions (Eubanks, 2018; Majumder and Mondal, 2021; Shum et al., 2018).”
Microlearning in teaching English to students of engineering specialities
Tolstykh, O. M., Pankova, V., & Krasnova, E. (2021) · E3S Web of Conferences · doi:10.1051/e3sconf/202127312136 · Cited by 9
Tickling Proactivity: Exploring the Use of Humor in Proactive Voice Assistants
Zargham, N., Reicherts, L., Avanesi, V., Rogers, Y., & Malaka, R. (2023) · International Conference on Mobile and Ubiquitous Multimedia (MUM) · doi:10.1145/3626705.3627777 · Cited by 12
“Recent research has shown that using humor by CAs enhances service satisfaction [77] and can potentially improve user engagement [78].”
BackgroundEarly Beginnings of AI: The Field of Research in Computer Science
Anurag, A. S. (2024) · Advances in business information systems and analytics book series · doi:10.4018/979-8-3693-2643-5.ch001 · Cited by 11
The Personification of ChatGPT (GPT-4)—Understanding Its Personality and Adaptability
Stöckli, L., Joho, L., Lehner, F., & Hanne, T. (2024) · Information · doi:10.3390/info15060300 · Cited by 18
VICA, a visual counseling agent for emotional distress
Sakurai, Y., Ikegami, Y., Sakai, M., Fujikawa, H., Tsuruta, S., González, A. J., Sakurai, E., Damiani, E., Kutics, A., Knauf, R., et al. (2019) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-019-01180-x · Cited by 9
“Our comparison metrics is also an adaptation of the one used in (Shinozaki et al. 2013): it is based on the dialogue continuation length (the average number of statements while a dialogue session is continuing) called CPS (Conversation-turns Per Session) in (Shum et al. 2018).”
BackgroundMethodInfluentialDevelopment and testing of an FPT.AI-based voicebot
Tran, D. C., Nguyen, D. L., & Hassan, M. F. (2020) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v9i6.2620 · Cited by 9
“Nowadays, chatbots, an application of AI, are replacing humans in interacting with users of the systems [7-11].”
BackgroundWu, X., Jiang, N., & Wu, Y. (2020) · Workshop on Neural Generation and Translation (WNGT) · doi:10.18653/v1/2020.ngt-1.8 · Cited by 10
Cuadra, A., Tin, A. L., Moffat, G. T., Alexander, K., Downey, R. J., Korc‐Grodzicki, B., Vickers, A. J., & Shahrokni, A. (2022) · European Journal of Surgical Oncology · doi:10.1016/j.ejso.2022.11.011 · Cited by 10
Open Domain Chatbot Based on Attentive End-to-End Seq2Seq Mechanism
Salahudeen, S. A., Sun, Y., Abdullahi, A., & Umar, A. (2019) · International Conference on Algorithms, Computing and Artificial Intelligence (ACAI) · doi:10.1145/3377713.3377773 · Cited by 9
“Inspired by the Turing test 1950 [3], Joseph Weizenbaum developed and published Eliza 1956 [8,9].”
MethodDiversifying Task-oriented Dialogue Response Generation with Prototype Guided ParaphrasingPreprint
Lippe, P., Ren, P., Haned, H., Voorn, B., & de Rijke, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.03391 · Cited by 13
“TASK-ORIENTED dialogue systems (TDSs) are becoming more widespread [1, 2, 3]; they are being used in a wide range of applications, including information seeking, shopping assistants and chat bots [4, 5].”
BackgroundThe Use of Copyrighted Works by AI Systems: Art Works in the Data Mill
Sartor, G., Lagioia, F., & Contissa, G. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3264742 · Cited by 9
Gupta, A., Varun, Y., Das, P., Muttineni, N., Srivastava, P., Zafar, H., Chakraborty, T., & Nath, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.00509 · Cited by 15
“Though chatbots originated in the 1960s, its use as an AI assistant and widespread acceptance is a recent phenomenon (Shum et al., 2018).”
BackgroundTherapy Chatbot Powered by Artificial Intelligence: A Cognitive Behavioral Approach
Shetty, M., Shah, P., Shah, K., Shinde, V., & Nehete, S. P. (2023) · International Conference in Advances in Power, Signal, and Information Technology (APSIT) · doi:10.1109/apsit58554.2023.10201725 · Cited by 8
“The authors argued that chatbots like Replika could potentially create unrealistic expectations of what technology can provide in terms of emotional support, and could also exacerbate existing social inequalities by providing access to emotional support only to those who can afford it [17].”
BackgroundEvaluating the Contribution of New Factors in the Assessment of eHealth Therapeutic Alliance
Ashur, O., Muench, F. J., & Baumel, A. (2023) · Journal of Technology in Behavioral Science · doi:10.1007/s41347-023-00336-z · Cited by 8
“Recent studies on user-AI agent relationships highlight the role of perceived personality in establishing user confidence and trust (Shum et al., 2018; Sjödén et al., 2011).”
HACAN: a hierarchical answer-aware and context-aware network for question generation
Sun, R., Tao, H., Chen, Y., & Liu, Q. (2023) · Frontiers of Computer Science · doi:10.1007/s11704-023-2246-2 · Cited by 11
Hierarchical matching network for multi-turn response selection in retrieval-based chatbots
Ma, H., Wang, J., Lin, H., & Zhang, Y. (2021) · Soft Computing · doi:10.1007/s00500-021-05699-0 · Cited by 8
Li, J., Tao, C., Hu, H., Xu, C., Chen, Y., & Jiang, D. (2022) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3488560.3498404 · Cited by 9
“In this paper, we devote to investigating the retrieval-based dialogue systems, since retrieval-based dialogue systems is superior in fluency and diversity, and have been applied to some real products such as the social chatbot XiaoIce [26] from Microsoft and the E-commerce AliMe assist [14] from Alibaba.”
MethodSamsonovich, A. V. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-01328-8_3 · Cited by 8
Perrone, A., & Edwards, J. (2019) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3342775.3342799 · Cited by 8
“conversational partners for individuals, having chatted to millions on messaging platforms like Facebook and Whatsapp [7].”
BackgroundDynamic Composition for Conversational Domain Exploration
Szpektor, I., Cohen, D., Elidan, G., Fink, M., Hassidim, A., Keller, O., Kulkarni, S., Ofek, E. O., Pudinsky, S., Revach, A., et al. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366423.3380167 · Cited by 13
“Some works combine retrievalbased and generation-based models [23, 38, 42, 43, 55].”
BackgroundResponse Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues
Xu, R., Tao, C., Feng, J., Wu, W., Yan, R., & Zhao, D. (2021) · ACM Transactions on Information Systems · doi:10.1145/3462207 · Cited by 11
“Using ready-made sentences, they prevail in providing informative and fluent responses, thus being widely applied in many real products such as XiaoIce [33] from Microsoft and AliMe Assist [21] from Alibaba.”
BackgroundMethodConversational Agents in Organisations: Strategic Applications and Implementation Considerations
Patel, S., Chiu, Y.-T., Khan, M. S., Bernard, J.-G., & Ekandjo, T. A. T. (2021) · Journal of Global Information Management · doi:10.4018/jgim.20211101.oa53 · Cited by 12
Designing Interactive Chatbot Development Systems
Feine, J., Morana, S., & Maedche, A. (2020) · AIS Electronic Library (AISeL) · Cited by 15
Svikhnushina, E., & Pu, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.13883 · Cited by 19
“…frequently mentioned components comprising a conversational agent’s naturalness are: responding coherently with the preceding context [6, 9, 10, 11, 12], anticipating user needs and questions [6, 9, 12], understanding culture-or language-specific terms [8, 11], facilitating input and response…”
BackgroundInfluentialLi, Z., Wu, C., Li, J., & Yuan, Q. (2025) · Aslib Journal of Information Management · doi:10.1108/ajim-05-2024-0427 · Cited by 14
Understanding Attachment to Social Chatbots: The Roles of Loneliness, Self‐Disclosure, and Empathy
Yao, R., & Nan, Y. (2025) · Journal of Consumer Behaviour · doi:10.1002/cb.70077 · Cited by 11
Gupta, S., Saxena, S., & Kataria, S. (2025) · Psychology and Marketing · doi:10.1002/mar.70093 · Cited by 11
Chatbot Design Challenges and the Effect on User Behavior
Almutairi, S., Khan, S., Kuhail, M. A., & Taj, I. (2023) · Advances in web technologies and engineering book series · doi:10.4018/978-1-6684-6234-8.ch002 · Cited by 7
You Go First: The Effects of Self-Disclosure Reciprocity in Human-Chatbot Interactions
Croes, E. A. J., Antheunis, M. L., & He, L. (2023) · International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) · doi:10.1109/aciiw59127.2023.10388091 · Cited by 12
“It is important for social chatbots to understand its users and to identify a user’s emotions and needs from a conversation [29].”
BackgroundAssessing LLMs Responses in the Field of Domestic Sustainability: An Exploratory Study
Giudici, M., Abbo, G. A., Belotti, O., Braccini, A., Dubini, F., Izzo, R. A., Crovari, P., & Garzotto, F. (2023) · International Conference on Digital Data Processing (DDP) · doi:10.1109/ddp60485.2023.00019 · Cited by 20
“As a rule-based model, ELIZA used predefined rules and lexicons for language generation and comprehension, exploiting the concept of pattern matching [38] that set up the stage for advanced models.”
MethodIce Cream in the Cathedral: The Literary Failures and Social Success of Chinese Robot Poet Xiao Bing
Krenz, J. (2020) · Asiatische Studien – Études Asiatiques · doi:10.1515/asia-2019-0024 · Cited by 7
LGBTQ-AI? Exploring Expressions of Gender and Sexual Orientation in Chatbots
Edwards, J., Clark, L., & Perrone, A. (2021) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3469595.3469597 · Cited by 10
“While many chatbot implementations have specific contexts for use, such as sales or customer service, recent work has shown both the popularity of chatbots that function only as social companions [26] as well as subversive uses for chatbots as performers in media, roles that they were not”
BackgroundAlghamdi, E., & Alnanih, R. (2021) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2021.0121077 · Cited by 8
“The chatbot is a conversational agent that interacts with users using natural language [48].”
BackgroundMethodHefny, A. H., Dafoulas, G. A., & Ismail, M. A. (2021) · Novel Intelligent and Leading Emerging Sciences Conference (NILES) · doi:10.1109/niles53778.2021.9600547 · Cited by 10
Digital Trends in Asian Hotel Industry
Kaliappen, N., & Hassan, A. (2022) · Springer eBooks · doi:10.1007/978-981-16-5461-9_9 · Cited by 12
Automatic Article Commenting: the Task and DatasetPreprint
Qin, L., Liu, L., Bi, V., Wang, Y., Liu, X., Hu, Z., Zhao, H. Y., & Shi, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.03668 · Cited by 7
“…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 Response Selection with Hierarchical Curriculum LearningPreprint
Su, Y., Cai, D., Zhou, Q. S., Lin, Z., Baker, S., Cao, Y., Shi, S., Collier, N., & Wang, Y. (2020) · arXiv (Cornell University) · doi:10.17863/cam.84982 · Cited by 7
Xu, Z., & Zhang, X. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2508311 · Cited by 8
“Chatbots can establish emotional connections with users by fulfilling their needs for communication, affection, and social belonging (Shum et al., 2018).”
Kuhail, M. A., Mrabet, J., Hijazi, R., & Thomas, J. (2025) · Human Behavior and Emerging Technologies · doi:10.1155/hbe2/8825536 · Cited by 8
Meng, Y., Park, S.-C., & Um, G. (2025) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2025.104560 · Cited by 8
Sun, M., & Zhao, Z. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2594149 · Cited by 11
“Additionally, incidents of empathic failure (e.g., ID1’s experience of chatbots ignoring surgical complications) highlight the necessity of context-aware sentiment analysis—an issue rarely addressed in previous studies on older adult-oriented chatbots (Abdollahi et al., 2023; Shum et al., 2018).”
Mukherjee, P., Agarwal, M. K., & Chatterjee, S. (2026) · Journal of Consumer Behaviour · doi:10.1002/cb.70115 · Cited by 6
Gao, M., Li, M., Ji, T., Wang, N., Lin, G., & Wu, Q. (2023) · Processes · doi:10.3390/pr12010058 · Cited by 9
“ELIZA [1], developed by Joseph Weizenbaum in the 1960s, was the first chatbot designed to simulate a conversation between a psychotherapist and a patient.”
BackgroundZhao, Y., Kong, X., Zheng, W., & Ahmad, S. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.1814 · Cited by 13
“Shum, He & Li (2018) used common-sense knowledge for emotion recognition.”
BackgroundZhao, M., Wang, L., Jiang, Z., Liu, Y., Li, R., Hu, Z., & Lu, X. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111843 · Cited by 11
Phan, Q. N., Tseng, C.-C., Le, T. H. T., & Nguyen, T. B. N. (2022) · AI & Society · doi:10.1007/s00146-022-01416-z · Cited by 14
“2021; Huang and Chueh 2021) human-likeness or emotional connection (Shum et al. 2018; Kuberkar and Singhal 2020), professional appearance (Følstad et al.”
BackgroundAvishka, W., Kuhaneswaran, B., & Gunasinghe, H. N. (2022) · International Conference on Advanced Research in Computing (ICARC) · doi:10.1109/icarc54489.2022.9753725 · Cited by 6
Strathearn, C., & Gkatzia, D. (2022) · DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc) · doi:10.18653/v1/2022.dialdoc-1.21 · Cited by 10
Liu, Y., Mayfield, R., & Huang, Y. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579602 · Cited by 9
Improving Retrieval-Based Dialogue System Via Syntax-Informed Attention
Song, T., Chen, N., Jiang, J., Zhu, Z., & Zou, Y. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095548 · Cited by 8
“Among mainstream types of dialogue systems, retrieval-based dialogue systems, such as Microsoft XiaoIce [1] and Alibaba AliMe Assist [2], that involve choosing optimal response from a set of candidates pool are widely used due to its rich response informativeness.”
MethodWu, Y., Zeng, Z., He, K., Mou, Y., Wang, P., Yan, Y., & Xu, W. (2022) · doi:10.18653/v1/2022.seretod-1.5 · Cited by 6
ChatGPT Media Coverage Metrics; Initial Examination
Delellis, N. S., Chen, Y., Cornwell, S., Kelly, D., Mayhew, A., Onaolapo, S., & Rubin, V. L. (2023) · Proceedings of the Association for Information Science and Technology · doi:10.1002/pra2.903 · Cited by 6
Emotionally Situated Text-to-Speech Synthesis in User-Agent Conversation
Liu, Y., Zhang, H., Liu, S., Yin, X., Ma, Z., & Jin, Q. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3613823 · Cited by 13
@llegra: a chatbot for Vallader
Bendel, O., & Jabou, D. (2024) · International Journal of Information Technology · doi:10.1007/s41870-024-01779-0 · Cited by 8
“Chatbots can be traced back to Alan Turing or Joseph Weizenbaum, depending on the narrative [16–18].”
Machine Learning in Text Analysis
Garg, N., & Sharma, K. (2020) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-5225-9643-1.ch018 · Cited by 6
GEDİK, Y. (2023) · Journal of Business and Communication Studies · doi:10.29228/jobacs.68836 · Cited by 9
Doğruöz, A. S., & Skantze, G. (2021) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/2021.sigdial-1.41 · Cited by 13
Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence ModelPreprint
Li, W., Xu, J., He, Y., Yan, S., Wu, Y., & Sun, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.01231 · Cited by 6
“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).”
BackgroundCan You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational AgentsPreprint
Wang, Y., Papangelis, A., Wang, R., Feizollahi, Z., Tür, G., & Kraut, R. E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.14653 · Cited by 15
“In order to have extended human-like conversations, some researchers have studied how to incorporate social language into chatbots to generate proper interpersonal responses and build an emotional connection with users [61].”
BackgroundChatbots and Health: Mental Health
Cheng, Y., Xie, C., Wang, Y., & Jiang, H. (2022) · Wiley eBooks · doi:10.1002/9781119678816.iehc0725 · Cited by 9
Wang, J., Ma, B., Nan, Y., He, Y., Sun, H., Liu, C., Tao, S., Qi, Q., & Liao, J. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3532663 · Cited by 6
“Building dialogue system such as a chatbot that can naturally communicate with human beings on open-domain topics is a very challenging problem in the field of artificial intelligence [1], [2], [3], [4], [5].”
Mental Health Support Using Gen-AI Shot Prompting Technique and Vector Embeddings
S., P., Deep, H., & Yadav, D. (2025) · International Conference on Data Science and Business Systems (ICDSBS) · doi:10.1109/icdsbs63635.2025.11031881 · Cited by 6
“Shum et al. [11] investigated issues of creating social chatbots like XiaoIce.”
“I Hadn't Thought About That”: Creators of Human-like AI Weigh in on Ethics & Neurodivergence
Rizvi, N., Smith, T., Vidyala, T., Bolds, M., Strickland, H., Begel, A., Williams, A., & Munyaka, I. N. S. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732218 · Cited by 8
Zhou, J., Shen, R., You, Y., DiSalvo, C. F., Dombrowski, L. S., & MacLellan, C. J. (2025) · Designing Interactive Systems Conference · doi:10.1145/3715336.3735831 · Cited by 12
“Chatbots have been deployed across various fields, such as open domain [41, 59, 78, 85], health care [31, 36], education [11, 23, 90], and customer service [7, 50].”
A counselor-inspired agent framework for AI counselors to enhance client engagement
Tang, Y., Kang, Y., Wang, Y., Wang, T. Y., Zhong, C., & Gong, J. (2025) · Technology in Society · doi:10.1016/j.techsoc.2025.103045 · Cited by 15
A Multi-Agent Chatbot Architecture for AI-Driven Language Learning
Aleedy, M., Atwell, E., & Meshoul, S. (2025) · Applied Sciences · doi:10.3390/app151910634 · Cited by 11
Autonomous AI Agents for Multi-Platform Social Media Marketing: A Simultaneous Deployment Study
Ahn, J., & Kim, M. (2025) · Electronics · doi:10.3390/electronics14214161 · Cited by 15
Li, L., Wang, T., Wang, Y., Wang, Y., & Zeng, X. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2618563 · Cited by 10
“Moreover, CAI has found applications in mental health support (Miner et al., 2020; Shum et al., 2018) and virtual companionship (Siemon et al., 2022; Xie & Pentina, 2022).”
Can chatbot companions alleviate loneliness in autistic users? evaluating digital companions
Hollis, A. S., McKenna-Plumley, P. E., Roman, R. B., & McKeown, G. J. (2026) · AI & Society · doi:10.1007/s00146-026-02877-2 · Cited by 8
“…scaffolding progression towards reciprocal human connection, the chatbot may lead to ‘emotional de-skilling’, serving to insulate the user from the very forms of discomfort that facilitate relational learning and contribute to the development of relationships with other people (Shum et al. 2018).”
SAM: Multi-turn Response Selection Based on Semantic Awareness Matching
Zhang, R., Wu, T., Wen, S., Nepal, ., Paris, C. L., & Xiang, Y. (2022) · ACM Transactions on Internet Technology · doi:10.1145/3545570 · Cited by 5
“Some works developed chatbots to have a long-time conversation with humans in a natural approach [19, 32].”
BackgroundApplications of Chatbots in Education
Ghayoomi, M. (2023) · Advances in web technologies and engineering book series · doi:10.4018/978-1-6684-6234-8.ch004 · Cited by 9
Eğitim Amaçlı Tasarlanan Sohbet Robotları Üzerine Yapılan Çalışmaların İncelenmesi
Cevher, A. Y., & Yıldırım, S. (2024) · Türk Eğitim Bilimleri Dergisi · doi:10.37217/tebd.1301877 · Cited by 6
A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation
Song, H., Zhang, W., Zhang, K., & Liu, T. (2022) · ACM Transactions on Information Systems · doi:10.1145/3563389 · Cited by 7
“Recently, dialogue systems are also of growing importance in facilitating smooth interactions be-tween humans and their information devices [12], and there emerges a series of well-known applications, such as social bot XiaoIce [40], and intelligent personal assistants Apple Siri and Amazon Alexa.”
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.