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 401–500 of 746
Knowledge-Enriched Domain Specific Chatbot on Low-resource Language
Perdana, R. S., Adikara, P. P., Indriati, I., & Kurnianingtyas, D. (2022) · Electrical Power, Electronics, Communications, Controls and Informatics Seminar (EECCIS) · doi:10.1109/eeccis54468.2022.9902930 · Cited by 6
“[18] presents the process a text input from user messages then passes the interpreter, the dialog manager, and response generator.”
BackgroundIntegrating Chatbot Media Automations in Professional Journalism: An Evaluation Framework
Kotenidis, E., Vryzas, N., Veglis, A. A., & Dimoulas, C. A. (2022) · Future Internet · doi:10.3390/fi14110343 · Cited by 8
AI-Enabled Conversational Agents in Service of Mild Cognitive Impairment Patients
Kostis, I.-A., Karamitsios, K., Kotrotsios, K., Tsolaki, M., & Tsolaki, A. (2022) · International Conference on Electrical and Information Technology (IEIT) · doi:10.1109/ieit56384.2022.9967865 · Cited by 5
“In their 2018 study, Shum et al.[20] provide insight in the course of evolution of primal CAs into modern, highly interactive ones.”
BackgroundRecent Advances in Chatbot Algorithms, Techniques, and Technologies: Designing Chatbots
Caldarini, G., & Jaf, S. (2023) · Advances in web technologies and engineering book series · doi:10.4018/978-1-6684-6234-8.ch011 · Cited by 6
González, A. L., Geiskkovitch, D. Y., & Young, J. E. (2023) · i-com · doi:10.1515/icom-2022-0047 · Cited by 5
“, 2018); research continues to explore novel designs and approaches (e.g., Abd-Alrazaq et al., 2020; Fitzpatrick et al., 2017; Hirano et al., 2017; Jeong et al., 2022; Luo et al., 2022; Nakagawa et al., 2013; Shum et al., 2018).”
BackgroundCan Chatbot Anthropomorphism and Empathy Mitigate the Impact of Customer Anger on Satisfaction?
Tang, J., Wang, Y., Zhou, X., Guo, J., & Li, C. P. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-57850-2_7 · Cited by 7
Digital Confessions: Exploring the Role of Chatbots in Self-Disclosure
van der Lee, C., Croes, E. A. J., de Wit, J., & Antheunis, M. L. (2019) · Research portal (Tilburg University) · Cited by 5
Home Assistant of The Future: What is It Like?
Bylieva, D. S., Bekiroğulları, Z., Lobatyuk, V. V., & Anosova, N. (2020) · Proceedings of the International Scientific Conference - Digital Transformation on Manufacturing, Infrastructure and Service · doi:10.1145/3446434.3446540 · Cited by 6
“Social chatbot has made significant progress in the field of emotional intelligence, taking into account the characteristics of the user and driving the conversation to a positive, desired topic through carefully generated responses [43].”
BackgroundPlanning Habit: Daily Planning Prompts with Alexa
Cuadra, A., Bankole, O., & Sobolev, M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-79460-6_7 · Cited by 9
NICE: Neural Image Commenting with Empathy
Chen, K., Huang, Q., McDuff, D., Gao, X., Palangi, H., Wang, J., Forbus, K. D., & Gao, J. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.380 · Cited by 11
“…in the domains of image captioning, visual question answering, visual dialog and visual storytelling (Mao et al., 2015; Vinyals et al., 2015; Devlin et al., 2015; Chen and Zitnick, 2015; Donahue et al., 2015; Karpathy and Fei-Fei, 2015; Kiros et al., 2014a,b; Gao et al., 2019; Shum et al., 2018).”
BackgroundSequential or jumping: context-adaptive response generation for open-domain dialogue systems
Ling, Y., Zheng, L., Wang, T., Cai, F., & Chen, H. (2022) · Applied Intelligence · doi:10.1007/s10489-022-04067-1 · Cited by 6
“While open-domain dialogue systems [11, 30, 54] focus on performing natural interactions on various openended topics, whose ultimate goal is to build long-term relationships with humans.”
BackgroundArtificial intelligence enabled conversational agent for mental healthcare
Omarov, B. S., Narynov, S., Zhumanov, Z., Alzhanova, E., Gumar, A., & Khassanova, M. (2022) · International Journal of Health Sciences · doi:10.53730/ijhs.v6n3.13239 · Cited by 7
“Additionally, text-based conversational agents like Ruth or Xiaoice have grown in popularity since they allow for private interactions (Shum et al., 2018).”
BackgroundKošecká, D., & Balco, P. (2023) · Studies in systems, decision and control · doi:10.1007/978-3-031-25695-0_26 · Cited by 5
Focus-Constrained Attention Mechanism for CVAE-based Response Generation
Cui, Z. M., Li, Y., Zhang, J., Cui, J., Chen, W., & Wang, B. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.183 · Cited by 5
An Adaptive Response Matching Network for Ranking Multi-turn Chatbot Responses
Wang, D., & Fang, H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-51310-8_22 · Cited by 5
Smart Wonder: Cute, Helpful, Secure Domestic Social Robots
Dereshev, D. (2018) · Northumbria Research Link (Northumbria University) · Cited by 7
Multi-Task Learning with Language Modeling for Question GenerationPreprint
Zhou, W., Zhang, M., & Wu, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.11813 · Cited by 11
“…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.”
An ontology-based chatbot for crises management: use case coronavirusPreprint
Hwerbi, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.02340 · Cited by 5
“of anger is high [52].”
Proto: A Neural Cocktail for Generating Appealing ConversationsPreprint
Saha, S., Das, S., Soper, E., Pacquetet, E., & Srihari, R. K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.02513 · Cited by 10
“Commercial conversational systems like Microsoft Xiaoice [21, 22] has been successful in crossing a 600 million worldwide user base.”
BackgroundThunström, A. O., Ali, L., Carlsen, H. K., Bohm, M., Wesén, L., Wrede, O., Vuković, I. S., Hellström, A., Larson, T., & Steingrímsson, S. (2025) · JMIR Formative Research · doi:10.2196/66163 · Cited by 5
Multimodal Expressive Embodied Conversational Agent Design
Jolibois, S., Ito, A., & Nose, T. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-35989-7_31 · Cited by 6
Channel-Aware Decoupling Network for Multiturn Dialog Comprehension
Zhang, Z., Zhao, H., & Liu, L. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3220047 · Cited by 5
“Since the responses of retrieval-based are generally more natural, fluent, and syntactically correct, retrieval-based methods are more mature for producing multiturn dialog systems both in acad-emia and industry [20], [21], [22], which is our major focus in this work.”
BackgroundEnhancing Paraphrase Question Generation With Prior Knowledge
Xie, J., Fang, W., Huang, Q., Cai, Y., & Wang, T. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3221045 · Cited by 6
“ChatbotssuchasMicrosoft XiaoIce[3]mayaskhumansalotofquestionsintheircommu-nication.”
Naous, T., Bassyouni, Z., Mousi, B., Hajj, H. M., Hajj, W. E., & Shaban, K. B. (2023) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3579164 · Cited by 6
“Early attempts in building open-domain models relied on developing Natural Language Processing (NLP) modules for utterance understanding and generation, and a dialog manager to switch between modules [15, 31, 40].”
BackgroundA Personalized Multi-Turn Generation-Based Chatbot with Various-Persona-Distribution Data
Zhu, S., Ma, T., Rong, H., & Al-Nabhan, N. (2023) · Applied Sciences · doi:10.3390/app13053122 · Cited by 6
Mou, Y., Wang, P., He, K., Wu, Y., Wang, J., Wu, W., & Xu, W. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.494 · Cited by 4
Debiasing Counterfactual Context With Causal Inference for Multi-Turn Dialogue Reasoning
Wang, X., Zhang, H., Zhao, S., Chen, H., Ding, Z., Wan, Z., Cheng, B. H., & Lan, Y. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3343608 · Cited by 7
“In reality, dialogue systems often generate logically contradictory dialogues [1], [19].”
BackgroundChatbot-based Tourist Guide Using Artificial Intelligence Markup Language
Ali, A. A., Kaka-Khan, K., & Al-chalabi, I. A.-C. (2023) · The Journal of The University of Duhok · doi:10.26682/csjuod.2023.26.2.52 · Cited by 5
Subaveerapandiyan, A., Kataria, S., Karthiga, S. V., & Sundaram, S. R. (2024) · Advances in library and information science (ALIS) book series · doi:10.4018/979-8-3693-2782-1.ch010 · Cited by 5
Aslan, A. (2025) · Pamukkale University Journal of Social Sciences Institute · doi:10.30794/pausbed.1559251 · Cited by 5
Probabilistic Verb Selection for Data-to-Text Generation
Zhang, D., Yuan, J., Wang, X., & Foster, A. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00038 · Cited by 5
“It is not difficult to imagine that different kinds of such data-to-text NLG systems can be utilized by a modern chatbot like Amazon Echo or Microsoft XiaoIce (Shum et al., 2018) to enable users access a variety of online data resources via natural language conversation.”
BackgroundA Study of Artificial Social Intelligence in Conversational Agents
Satyanarayana, V., Shankar, S., Sruthi, V., & Das, B. (2018) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict43934.2018.9034313 · Cited by 4
“Shum et al. [7] have presented a brief survey of conversational systems - from Eliza and early chatbots meant for psychotherapy to task completion agents specific to a particular domain, intelligent personal agents like Siri and Cortana and the more recent Microsoft Product - XiaoIce, a social…”
BackgroundTowards Higher Customer Conversion Rate: An Interactive Chatbot Using the BEET Model
Badawy, W., El-Helw, A., & Youssif, A. A. A. (2020) · International Conference on Consumer Electronics · doi:10.1109/icce-berlin50680.2020.9352152 · Cited by 8
“Chatbots have been developed as increased interest in automation [4], [5].”
BackgroundA Background Knowledge Revising and Incorporating Dialogue Model
Zhao, X., Feng, X., & Chen, H. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3123128 · Cited by 5
“Due to the practical benefit, it has been widely applied in the commercial chatbots such as the social bot XiaoIce [13] and the online shopping assistant AliMe Assist from Alibaba Group [14]. tasks.”
MethodMemory Efficient Knowledge Base Question Answering with Chatbot Framework
Japa, S. S., & Rekabdar, B. (2021) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm52142.2021.00013 · Cited by 5
Zeng, H., Wei, B., Liu, J., & Fu, W. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.500 · Cited by 14
“It plays a vital role in knowledge testing (Heilman and Smith, 2010; Lindberg et al., 2013; Ghanem et al., 2022) and information seeking (Shum et al., 2018; Rosset et al., 2020; Zamani et al., 2020) by creating quiz questions and spanning question suggestions, respectively.”
BackgroundOverview of the NLPCC 2022 Shared Task: Multi-modal Dialogue Understanding and Generation
Wang, Y., Zhao, X., & Zhao, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17189-5_29 · Cited by 4
Outfit Helper: A Dialogue-Based System for Solving the Problem of Outfit Matching
Zhang, B., & Wang, Q. (2019) · Journal of Computer and Communications · doi:10.4236/jcc.2019.712006 · Cited by 4
“Researchers have successfully developed many chatbots based on NLP1, such as ELIZA [1], XiaoIce [2], PARRY, and Racter, among others.”
Length Adaptive Regularization for Retrieval-based Chatbot Models
Wang, D., & Fang, H. (2020) · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR) · doi:10.1145/3409256.3409823 · Cited by 4
“Moreover, chatbots have started playing an increasingly important role in many real-world applications such as customer support and tutoring systems [1, 11, 14].”
BackgroundLet's Ask Again: Refine Network for Automatic Question GenerationPreprint
Nema, P., Mohankumar, A. K., Khapra, M. M., Srinivasan, B. V., & Ravindran, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.05355 · Cited by 14
“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).”
MethodHumour-in-the-loop: Improvised Theatre with Interactive Machine Learning Systems
Mathewson, K. W. (2019) · ERA: Education and Research Archive (University of Alberta) · doi:10.7939/r3-dn4w-bw61 · Cited by 9
The Future of Artificial Intelligence and its Social, Economic and Ethical ConsequencesPreprint
Hussein, B. R., Chongomweru, H., & Siddique, M. T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.03366 · Cited by 9
“Take an example of recognizing object from images which just seemed like a sci-fi of AI a few years ago but now a simple convolutional neural network sits at the back and does the work [6].”
BackgroundKrämer, N. C., Kühn, T., & Horstmann, A. C. (2025) · ACM International Conference on Intelligent Virtual Agents (IVA) · doi:10.1145/3717511.3747077 · Cited by 5
“Social chatbots are not designed to address specific problems in predefined scenarios but rather to engage in open, social conversations with users on any topic [25].”
Iovane, G., Fominska, I., & Pasquale, R. D. (2025) · Algorithms · doi:10.3390/a18110721 · Cited by 4
“The research work in [26] established sev‑ eral principles for human coordination with AI training in psychological applications that very clearly identified the need for transparency, rigorous theoretical frameworks, bound‑ aries appropriate to the AI capacities, and other important principles…”
Deng, J., Zhang, W., Jiao, Z., & Ren, F. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791186 · Cited by 5
Are AI Companions Real Companions? A BERT ‐Based Study of Replika Reviews
Gautam, C., & Kumar, P. (2026) · Journal of Consumer Behaviour · doi:10.1002/cb.70161 · Cited by 5
Thiele, F. (2024) · Journal of Creative Communications · doi:10.1177/09732586241281018 · Cited by 4
“Both of them can respond to users requests and are able to establish emotional connections with users by simulating human communication in a text-or audio-based form (Shum et al., 2018; Stäcker & Stanoevska-Slabeva, 2018).”
Reviewing chatbot algorithms: methods for intelligent dialogue systems
Lavlu, M. T. H., Hassan, A., Akhtar, S., Labiba, S. B., & Mustafa, H. A. (2025) · Human-Intelligent Systems Integration · doi:10.1007/s42454-025-00074-y · Cited by 3
“Rule-based systems, such as those used in early chatbots like ELIZA, are highly interpretable and predictable but lack scalability and adaptability (Shum et al. 2018).”
Development of a mobile application for occupant-centric facility maintenance management
Alhaj, M. B., Liu, H., Abudayyeh, O. Y., & Sulaiman, M. (2022) · IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot54504.2022.9817248 · Cited by 8
CAAS (Chatbot as a Service): Sector-Wise Survey
Bhalshankar, S. V., & Deshmukh, R. R. (2023) · Advances in computer science research · doi:10.2991/978-94-6463-136-4_11 · Cited by 4
Label-Guided Contrastive Learning for Out-of-Domain Detection
Zhang, S., Li, T., Bai, J., & Li, Z. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095333 · Cited by 5
“Given a user utterance, the task aims to identify whether a query falls outside the predefined intent set[1, 2, 3].”
BackgroundExploring Ethical Dimensions of AI Assistants and Chatbots
Porna, S. B., Ahmad, M., Vallejo, R. G., Shahzadi, I., & Rahman, M. A. (2024) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-9173-0.ch011 · Cited by 6
Kaneho, A. E. A., Zrira, N., Ouazzani-Touhami, K., Khan, H. A., & Nawaz, S. (2025) · Intelligence-Based Medicine · doi:10.1016/j.ibmed.2025.100261 · Cited by 7
Chierici, A., Habash, N. Y., & Bicec, M. (2020) · Language Resources and Evaluation · Cited by 3
An Exploratory Study on Chatbots
Bhattacharjya, A., Punyamurthi, A., Lakshmi, S. A., Iragala, A., Thallapureddy, M. C., & Kannaiah, S. K. (2022) · International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS) · doi:10.1109/ice3is56585.2022.10010154 · Cited by 3
Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
Chi, E. A., Paranjape, A., See, A., Chiam, C., Chang, T., Kenealy, K., Lim, S. K., Hardy, A., Rastogi, C., Li, H., et al. (2022) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/2022.sigdial-1.37 · Cited by 13
A Prospective-Performance Network to Alleviate Myopia in Beam Search for Response Generation
Wang, Z., Bai, Y., Wu, B., Xu, Z. X., Wang, Z., & Wang, B. (2018) · International Conference on Computational Linguistics · Cited by 3
On Generating Fact-Infused Question Variations
Deschamps, A., Gollapalli, S. D., & Ng, S.-K. (2021) · International conference Recent advances in natural language processing · doi:10.26615/978-954-452-072-4_039 · Cited by 5
“Viewed as the reverse of the well-studied question answering task (QA), QG has been applied in education and tutoring (Heilman and Smith, 2010; Lindberg et al., 2013), dialog systems and chatbots (Shum et al., 2018), as well as for improving QA systems (Duan et al., 2017; Tang et al., 2018).”
BackgroundI Know You Better: User Profile Aware Personalized Dialogue Generation
Dong, W., Feng, S., Wang, D., & Zhang, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-95408-6_15 · Cited by 3
Yamamoto, K., Inoue, K., & Kawahara, T. (2022) · Computer Speech & Language · doi:10.1016/j.csl.2022.101469 · Cited by 4
Artificial Intelligence Based Chatbot for Healthcare Applications
Nimal, K. A., Nair, V. V., Jegdeep, R., & Nehru, J. A. (2023) · Advances in science and technology · doi:10.4028/p-atr6jg · Cited by 5
“The solution, along with a question from conversation index [12,33] As a result, the user's output is returned to them.”
BackgroundNeural Response Generation with Meta-WordsPreprint
Xu, C., Wu, W., Tao, C., Hu, H., Schuerman, M., & Wang, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.06050 · Cited by 3
“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…”
BackgroundChatbots language design: the influence of language variation on user experiencePreprint
Chaves, A. P., Egbert, J., Hocking, T. D., Doerry, E., & Gerosa, M. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.11089 · Cited by 3
“Previous literature has shown the benefits of personalized interactions with chatbots [39, 114, 123], particularly in domains where the chatbot needs to build rapport and trustful relationships with the user, such as in financial services [38], companion (or buddy) chatbots [114, 123], and recommendation systems [25].”
BackgroundDialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based ChatbotsPreprint
Li, J., Liu, C., Tao, C., Chan, Z., Zhao, D., Zhang, M., & Yan, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.09534 · Cited by 3
“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].”
BackgroundYou and I plus AI: A qualitative exploration of replika in the context of human relationships
Rodger, K., & Field, E. F. (2025) · The Canadian Journal of Human Sexuality · doi:10.3138/cjhs-2025-0011 · Cited by 3
“understand language and imagery, allows the AI conversational agent to gain the user’s trust and meet their emotional needs for affection and belonging (Shum et al., 2018).”
Taheri, A., Bhardwaj, P., Caetano, A., Zhong, A., & Sra, M. (2023) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3586182.3616680 · Cited by 5
“It is now plausible to consider the use of this technology as a means of mitigating social isolation [6, 7, 16, 17].”
BackgroundA large language model-based chatbot system framework for urban planners
Zhou, X., Jeong, B., & Chapple, K. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130307 · Cited by 2
Service recovery through anthropomorphic chatbots: a consumer face concern perspective
Hai, W., & Katsumata, S. (2025) · Asia Pacific Journal of Marketing and Logistics · doi:10.1108/apjml-06-2025-1270 · Cited by 2
Empathy in action: An empirical exploration of user perspectives on conversational agent empathy
Lee, B., Shin, Y., & Yoo, B. (2026) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2026.103797 · Cited by 4
Learning bi-utterance for multi-turn response selection in retrieval-based chatbots
Wang, S., Li, D., Geng, J., Yang, L., & Dai, T. (2019) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881419841930 · Cited by 3
Self-citationHow Much Emotionally Intelligent AI Can Be?
Szewczyk, R., & Janik, K. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-72254-8_5 · Cited by 2
Parnell, S. I., Klein, S. H., & Gaiser, F. (2022) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3543829.3544517 · Cited by 7
“Similarly, social chatbots, such as Replika or Kuki can help fulfill needs for “communication, affection, and social belonging” [38].”
BackgroundThe Evolution of Gendered Software: Products, Scientific Reasoning, Criticism, and Tools
Kratel, V. A. E. (2022) · Human-Machine Communication · doi:10.30658/hmc.5.5 · Cited by 6
Integrating A Dialogue Tree Based Turkish Chatbot into an Open Source Python Coding Editor
Bilgin, T. T., & Yavuz, E. (2022) · International Informatics and Software Engineering Conference (IISEC) · doi:10.1109/iisec56263.2022.9998250 · Cited by 2
“New generation chatbots can react to images and can also recognize objects in images, make comments about them and express their feelings [9].”
BackgroundQuestion Answering System Based on University Knowledge Graph
Leng, J., Yang, Y., Lin, R., & Tang, Y. Z. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-2385-4_12 · Cited by 2
Automatic Dialog Flow Extraction and Guidance
Ferreira, P. (2023) · Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop (EACL SRW) · doi:10.18653/v1/2023.eacl-srw.12 · Cited by 4
“Chatbots are the result of advances in Artificial intelligence (AI), in order to interact and respond with suggestions appropriate to certain needs (Shum et al., 2018).”
BackgroundAvishka, P., Ravikumar, N., Kuhaneswaran, B., & Gunasinghe, H. (2023) · Sabaragamuwa University Journal · doi:10.4038/suslj.v19i2.7792 · Cited by 2
“Nevertheless, chatbots like MILABOT, XiaoIce, and Mitsuku managed to emulate human-like interactions using intricate frameworks and advanced machine learning (Shum, He, Li, 2018).”
Transformative Conversational AI: Sentiment Recognition in Chatbots via Transformers
Noorani, S. H., Khan, S., Mahmood, A., Ishtiaq, M., Rauf, U., & Ali, Z. (2023) · International Multi-Topic Conference · doi:10.1109/inmic60434.2023.10465887 · Cited by 4
“It assumes a pivotal role in diverse applications such as sentiment analysis, chatbot development, and language translation [4].”
BackgroundPersona-Identified Chatbot through Small-Scale Modeling and Data Transformation
Keum, B., Sun, J., Lee, W., Park, S., & Kim, H. (2024) · Electronics · doi:10.3390/electronics13081409 · Cited by 3
Lee, H.-K., & Hwang, M. (2024) · The Journal of AsiaTEFL · doi:10.18823/asiatefl.2024.21.2.4.325 · Cited by 2
A Historical Analysis of Chatbots from Eliza to Google Bard
Singh, R., Thakur, J., & Mohan, Y. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-6726-7_2 · Cited by 6
Raj, K., Priya, K. M., Senthilkumar, K., Natarajan, S., Arun, R., & Thoti, K. K. (2024) · International Conference on Integrated Intelligence and Communication Systems (ICIICS) · doi:10.1109/iciics63763.2024.10859719 · Cited by 2
“Recurrent neural networks (RNNs) and transformer-based models (BERT, GPT) are examples of such models[7].”
Humanizing Customer Interaction: AI-Powered Experiences in the Digital Age
Deshpande, M. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-8009-3.ch017 · Cited by 4
Diyabet Yönetiminde Yapay Zeka Destekli Sanal Hemşirelerin Rolü ve Geleceği
Ceviz, A., & Özden, G. (2025) · Artuklu Health · doi:10.58252/artukluhealth.1577432 · Cited by 3
SQUbot: Enhancing Student Support Through a Personalized Chatbot System
Nadir, Z., Al-Lawati, H. M., Mohammed, R. A., Subhi, M. A., & Hossen, A. (2025) · Technologies · doi:10.3390/technologies13090416 · Cited by 8
Training Two-Stage Knowledge-Grounded Dialogues with Attention Feedback
Li, Z., Feng, J., Tao, C., & Zhao, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17120-8_37 · Cited by 2
Transformer Decoder Based Reinforcement Learning Approach for Conversational Response Generation
Faal, F., Yu, J. Y., & Schmitt, K. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207289 · Cited by 2
“…a system with the ability to understand natural language (hold the conversation with humans) has been one of the longest-running goals in the field of Natural Language Processing (NLP) and Artificial Intelligence (AI) in some sense dating back to the ELIZA project at MIT in the 1960s [1], [2].”
BackgroundCORE: Cooperative Training of Retriever-Reranker for Effective Dialogue Response Selection
Tao, C., Feng, J., Shen, T., Liu, C., Li, J., Geng, X., & Jiang, D. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.174 · Cited by 3
“In this paper, we concentrate on retrieval-based dialogue systems (Lowe et al., 2015; Boussaha et al., 2019; Yu et al., 2021; Su et al., 2021), which can deliver smooth and informative responses, and have powered industrial applications (Shum et al., 2018; Ram et al., 2018).”
BackgroundA variational selection mechanism for article comment generation
Liu, J., Cheng, P., Dai, J., & Liu, J. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121263 · Cited by 2
Sustainability through Artificial Intelligence in Oil and Gas Industry - A Case Study
Bangera, S., & Bhat, S. (2023) · International Journal of Case Studies in Business IT and Education · doi:10.47992/ijcsbe.2581.6942.0324 · Cited by 4
Singh, A. K., Sinha, S., Jagyasi, B. G., Abinaya, C. C., Mishra, S., Mylavarapu, R., Maripalli, H., Gawade, P., & Contractor, G. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-4828-4_16 · Cited by 2
Human-Artificial Systems Collaboration in Service Innovation and Social Inclusion
Zafar, A., & Ahola, M. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-68017-6_78 · Cited by 2
Predicting Question Responses to Improve the Performance of Retrieval-Based Chatbot
Wang, D., & Fang, H. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72240-1_44 · Cited by 2
Aguiar, L., Cruz, L. A., da Silva, T. L. C., do Carmo, R. A. F., & Paixão, M. H. E. (2022) · Simpósio Brasileiro de Bancos de Dados (SBBD) · doi:10.5753/sbbd.2022.224329 · Cited by 2
“Conversational systems, commonly known as chatbots, are software systems capable of having a conversation with a person, either textually or vocally [Shum et al. 2018].”
BackgroundEnriching Conversation Context in Retrieval-based ChatbotsPreprint
Tahami, A. V., & Shakery, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.02290 · Cited by 3
“Retrieval-based chatbots have also been used in real-world products such as Microsoft XiaoIce [21] and Alibaba Group’s Alime Assist [12].”
Transparency in Language Generation: Levels of AutomationPreprint
Edwards, J., Perrone, A., & Doyle, P. R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.06295 · Cited by 3
“While there is some evidence that people enjoy chatting with natural-sounding chatbots [14], other work casts doubt suggesting these preferences may be due to the novelty of the interaction [3], which may mean there are limited use-cases for this level of automation.”
BackgroundStrategyproof Learning: Building Trustworthy User-Generated DatasetsPreprint
Farhadkhani, S., Guerraoui, R., & Hoang, L. N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.02398 · Cited by 4
“[39] Heung-Yeung Shum, Xiaodong He, and Di Li.”
BackgroundZeng, Z., He, K., Yan, Y., Liu, Z., Wu, Y., Xu, H., Jiang, H., & Xu, W. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.14289 · Cited by 2
“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).”
BackgroundControllable Open-ended Question Generation with A New Question Type OntologyPreprint
Cao, S., & Wang, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.00152 · Cited by 2
“Questions generated by our model have diverse T YPE s. et al., 2019) and building open-domain dialogue systems (Shum et al., 2018).”
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.