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 501–600 of 746
Qiu, Y., Zhang, J., Ren, H., & Zhou, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.06538 · Cited by 2
“In recent years, building intelligent conversational agents (Shum et al., 2018; Kollar et al., 2018; Kim et al., 2020) is gaining more and more attention in the field of natural language processing.”
AI Conversational Agent Design for Supporting Learning and Well-Being of University StudentsPreprint
Wang, H., Tang, S., & Lei, C. (2024) · EdArXiv (OSF Preprints) · doi:10.35542/osf.io/w4rtf · Cited by 4
Computer love: AI-powered chatbots are changing how we understand romantic and sexual well-being
Lapointe, V. A., Dubé, S., & Lafortune, D. (2024) · The Conversation · doi:10.64628/aam.qcmutpnxg · Cited by 2
A Socially Emotional Virtual Registrar Based on eBICA and Deep Learning
Anisimova, A. S., Mikhnev, A. O., Tsarkov, V. S., Dolgikh, A. A., & Samsonovich, A. V. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.11.128 · Cited by 1
Someone Like Us: Anthropomorphism in the Consumer Behavior in the Scope of Emerging Countries
Çizer, E. Ö. (2023) · Advances in human and social aspects of technology book series · doi:10.4018/978-1-6684-6873-9.ch012 · Cited by 3
Chatbot usability scale: Adaptation to turkish and validation/reliability analysis
Yavuz, M., Kayalı, B., Balat, Ş., & Çalışan, M. (2023) · i-manager’s Journal on Educational Psychology · doi:10.26634/jet.20.1.19758 · Cited by 1
SOCIAL COMPANION CHATBOT FOR HUMAN COMMUNICATION USING ML AND NLP
Saransh, S. (2023) · International Journal of Engineering Applied Sciences and Technology · doi:10.33564/ijeast.2023.v08i01.048 · Cited by 3
AI Powered Virtual Stress Management Assistant for IT Professionals
Dharmagunarathna, S. J., Premarathne, D., Harishchandra, D., Ranasgala, C., Thilakarathne, T., & Harshanath, B. (2023) · International Conference on Advancements in Computing (ICAC) · doi:10.1109/icac60630.2023.10417469 · Cited by 1
Business and Optimization Applications Using AI Chatbots
Özbek, H. E., & Demircioğlu, M. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-55911-2_5 · Cited by 1
Neogi, S., Mukherjee, S., & Verma, A. (2024) · Advances in logistics, operations, and management science book series · doi:10.4018/979-8-3693-5503-9.ch017 · Cited by 1
Nikitin, D., & GOLIAN, V. (2025) · Herald of Khmelnytskyi National University Technical sciences · doi:10.31891/2307-5732-2025-349-42 · Cited by 2
Enhancing Patient Intake Process in Mental Health Consultations Using RAG-Driven Chatbot
Shayaninasab, M., Zahoor, M., & Yalçın, Ö. N. (2024) · International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) · doi:10.1109/aciiw63320.2024.00053 · Cited by 5
“XiaoIce [14], an AI chatbot developed by Microsoft, is designed to engage in conversations with users, providing emotional support, companionship, and entertainment [15].”
Hossain, R., Khan, R. N., Chowdhury, P. S. R., Huda, S. M. M. M., & Ahmed, N. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93236-6_13 · Cited by 1
Hidayat, M. L., Ahmad, I., Assidiqi, M. H., Khanzada, T. J. S., & Meccawy, M. (2025) · International Conference on Innovation in Artificial Intelligence and Internet of Things (AIIT) · doi:10.1109/aiit63112.2025.11082869 · Cited by 2
“The most frequently cited articles in this cluster are [57]–[60].”
A Survey on Integration of Empathy Cues Into Empathetic Text Generation
Montiel-Vázquez, E. C., Cruz, C. A., Uresti, J. A. R., González-Mendoza, M., & Gómez, R. (2025) · IEEE Access · doi:10.1109/access.2025.3597304 · Cited by 2
“Using classification for empathy cues predates EMPATHETICDI-ALOGUES (ED) [13], as it is seen in antecedents such as XiaoIce [20], a large-scale chatbot which uses them to obtain user information.”
Rahmaniar, W., Haq, Q. M. U., Iskandar, M. E., & Ma’arif, A. (2025) · IT Professional · doi:10.1109/mitp.2025.3578694 · Cited by 1
Karim, B. Q., Massaoudi, E. M. E., Lamrhary, M. A., Elkhatibi, Y., Ahmed, E. H., & El-Ouali, A. (2025) · International Conference on Circuit, Systems and Communication (ICCSC) · doi:10.1109/iccsc66714.2025.11135178 · Cited by 1
“These innovations foster a climate of trust by giving employees the feeling that they are being listened to and supported in a period of transition that is sometimes anxiously changing [16].”
Is attributional style a marker of personification? A case study with ChatGPT
Norcia, M., & Colí, E. (2025) · Journal of Psychology and AI · doi:10.1080/29974100.2025.2569932 · Cited by 1
Humanizing AI - Enhancing User Engagement in Health Applications with Personality-Driven AI Design
Sudharsan, B., & Waxman, P. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-94940-1_11 · Cited by 1
Melillos, N., & Αγαπίου, Ά. (2026) · Heritage · doi:10.3390/heritage9010032 · Cited by 1
“These pioneering systems were followed by increasingly complex rule-based and retrieval-based models through the 1980s and 1990s, including Jabberwacky, ALICE, and Mitsuku, which used pattern databases and hand-crafted scripts to sustain conversation [10].”
InfluentialLy, N. T. H., NGUYEN, C. Q., Do, Q., & Dam, K. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70630 · Cited by 3
Hwang, L. J., Li, H., & Feng, B. (2026) · Behaviour and Information Technology · doi:10.1080/0144929x.2026.2633768 · Cited by 1
“Recent research has begun to investigate the impact of chatbots’ communication skills on user engagement (Schuetzler et al., 2020) and how social chatbots implement these skills to help accommodate user requests in human-chatbot social interactions (Shum et al., 2018; Zhou et al., 2020).”
Moon, J., Moon, J., Yun, J.-Y., & Yun, J.-Y. (2026) · Archives of Design Research · doi:10.15187/adr.2026.02.39.1.335 · Cited by 2
Virtual Love, Real Loss: The Losses in AI-Powered Romantic Relationships
Wu, Y. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-6623-4.ch007 · Cited by 1
History of chatbots and their emerging applications in textiles, polymers, and sustainability
Al-Amin, M., Hossain, M. E., Ali, M. S., Salam, A., Ali, A., Ullah, A., Alam, N., Akhter, M. N., & Mahmood, S. A. (2026) · Sustainable materials and technologies · doi:10.1016/j.susmat.2026.e01967 · Cited by 7
Hwang, L. J., Li, H., & Feng, B. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2669042 · Cited by 2
Jiang, Z. (2026) · Design and Artificial Intelligence · doi:10.1016/j.daai.2026.100087 · Cited by 3
Barriers Shaping Synthetic Relationships With Companion Bots: A Three-Week Initial Adaptation Study
Tschopp, M. V., Schlicker, N., Zargham, N., Sætra, H. S., & Schöning, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-26717-7_1 · Cited by 1
Functional Neural Networks in Behavioral Motivations
Orlov, V. A., Ushakov, V., Kartashov, S., Malakhov, D. G., Korosteleva, A. N., Skiteva, L. I., & Samsonovich, A. V. (2018) · Studies in computational intelligence · doi:10.1007/978-3-030-01328-8_33 · Cited by 1
Learning to balance the coherence and diversity of response generation in generation-based chatbots
Wang, S., Li, D., Geng, J., Yang, L., & Leng, H. (2020) · International Journal of Advanced Robotic Systems · doi:10.1177/1729881420953006 · Cited by 1
Self-citationProblems And Countermeasures Of Tax Collection And Management In E-Commerce
Wang, X. (2020) · Cited by 1
The practice of speech and language processing in China
Jia, J., Chen, W., Yu, K., He, X., Du, J., & Shum, H. (2021) · Communications of the ACM · doi:10.1145/3481625 · Cited by 1
“17,38 These techniques have successfully driven efficient, sustainable, and stable development, and aim to improve the future of the whole society. prosodic information unsupervised to decouple timbre and rhythm, which are considered as style, and a rhythm decoder, to predict the above prosody…”
Self-citationNatural Language Processing and Cloud Computing in Disease Prevention and Management
Ferreira, R., Gregório, P., Coelho, L. P., & Reis, S. S. (2022) · Advances in medical technologies and clinical practice book series · doi:10.4018/978-1-6684-5260-8.ch010 · Cited by 1
Przyjazny i formalny bot: poczucie wstydu i satysfakcji w komunikacji z botem pierwszego kontaktu
Wasilewski, J., & Kostrzewa, A. (2023) · Kultura - Media - Teologia · doi:10.21697/kmt.2023.54.07 · Cited by 1
Performance evaluation of keyword detection for the chatbot model
Gunnam, G. R., Inupakutika, D., Mundlamuri, R., Kaghyan, S., Akopian, D., Chalela, P., & Ramírez, A. G. (2023) · Electronic Imaging · doi:10.2352/ei.2023.35.3.mobmu-359 · Cited by 2
Integrando BPMN e AIML para construção de fluxos de diálogo para Chatbots
Neo, G. D. S., Barros, E. C., Neo, A. V. B. D. S., Moura, J. A. B., Correia, A. C., & Rodrigues, W. R. M. (2023) · Anais do Seminário Integrado de Software e Hardware (SEMISH) · doi:10.5753/semish.2023.230922 · Cited by 1
“Ela utilizava técnicas simples de casamento de padrão, mas surpreendeu a comunidade não científica com a sua capacidade em manter usuários conversando com o programa por longos períodos [Shum et al. 2018].”
BackgroundSynDG: Syntax-aware Dialogue Generation
Qiu, J., Zhang, H., & Yang, Y. (2023) · International Conference on Computing and Artificial Intelligence (ICCAI) · doi:10.1145/3594315.3594364 · Cited by 1
“1 Dialogue system Dialogue systems have attracted sensational attentions in both academy and industry communities with a wide range of application prospects, such as Eliza [27], Alice [4] and Microsoft XiaoIce [20].”
BackgroundIRRGN: An Implicit Relational Reasoning Graph Network for Multi-turn Response Selection
Deng, J., Dai, H., Guo, X., Ju, Y., & Peng, W. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.584 · Cited by 3
Survey: Unconventional Categories of Chatbots that make use of Machine Learning Techniques
Gandhi, S., & Patel, C. (2023) · Journal of Information Technology and Digital World · doi:10.36548/jitdw.2023.3.006 · Cited by 1
Perceptions of the Design and Use Chatbots for Educational Purposes: A Dialogue Partner
Černý, M. (2023) · The Journal of Educators Online · doi:10.9743/jeo.2023.20.4.3 · Cited by 9
“Chatbots or text-based dialogue systems have applications in many areas of human life (Brandtzaeg & Følstad, 2017; Jain et al., 2018; Shum et al., 2018).”
Wang, Y., Wang, Y., & Zhao, D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44699-3_37 · Cited by 2
O USO DA INTELIGÊNCIA ARTIFICIAL NA SOCIEDADE
Koppe, P. C., & Mäder, B. J. (2023) · doi:10.22533/at.ed.96523091017 · Cited by 1
Barachini, F., & Stary, C. (2023) · Journal of Information & Knowledge Management · doi:10.1142/s0219649223500703 · Cited by 1
An Efficient Matching Algorithm for Question Answering System
Zhang, J., Zhao, X. E., Huang, J., & Song, Y. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia231020 · Cited by 1
Wang, H., Kwan, W.-C., Li, M., Zhou, Z., & Wong, K. (2024) · Computer Speech & Language · doi:10.1016/j.csl.2024.101637 · Cited by 11
Large-scale digital signatures of emotional response to the COVID-19 vaccination campaign
Bertani, A., Gallotti, R., Menini, S., Sacco, P. L., & Domenico, M. D. (2024) · EPJ Data Science · doi:10.1140/epjds/s13688-024-00452-7 · Cited by 1
“Moreover, in online interactions some of the participants may be nonhuman (bots) which are explicitly designed to implement a certain strategy of affective communication to elicit types of emotional responses from users [24].”
Backgroundliu, J., Qin, Z., Zhang, Z., & Zhang, J. (2024) · International Journal of Computational Intelligence and Applications · doi:10.1142/s1469026824500068 · Cited by 1
People and machines in communication / Personas y máquinas en comunicación
Jacomuzzi, A. C., & Alioto, B. P. (2024) · Studies in Psychology Estudios de Psicología · doi:10.1177/02109395241241380 · Cited by 4
“Shum et al. (2018) analizaron las diferencias entre los tres sistemas, considerando ocho componentes: Escalabilidad temporal, Características principales, Logros e hitos, Modalidad, Modelado, Ámbito, Avance técnico clave y Limitación técnica clave.”
BackgroundInfluentialApplying Text Mining to Analyze Human Question Asking in Creativity Research
Wróblewska, A., Korbin, M., Kenett, Y. N., Dan, D., Ganzha, M., & Paprzycki, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-86193-2_4 · Cited by 3
“Beyond question measuring itself, the question analysis might also support automatic question generation tasks, which can reduce manual question creation costs and meet the growing demand for questions, particularly in education and in dialogue systems [35, 23].”
BankBot: Streamlined Banking Support Through Centralized FAQs
Kulkarni, R. V., Paldewar, A., Paliwal, S., Palwe, A., & Panchal, S. (2024) · International Conference on Progressive Innovations in Intelligent Systems and Data Science (ICPIDS) · doi:10.1109/icpids65698.2024.00030 · Cited by 1
“Studies have showcased significantly that chatbots trained with NLP can effectively reduce response times and enhance customer satisfaction [22].”
Chatting Away Loneliness: Embracing New Connections Between Humans and Artificial Intelligence
Vandhika, S., & Sahrani, R. (2025) · INSAN Jurnal Psikologi dan Kesehatan Mental · doi:10.20473/jpkm.v10i12025.1-20 · Cited by 6
Human-AI Interaction from an Evolutionary Neurosociological Perspective
Shkurko, Y. (2025) · Handbooks of sociology and social research · doi:10.1007/978-3-031-95615-7_21 · Cited by 2
Lee, J. (2025) · New Media & Society · doi:10.1177/14614448251338275 · Cited by 2
“…race, age, and so forth to create an “effect” of the chatbot personality on the user and make it more credible as a social actor (Natale, 2021: 102; Shum et al., 2018: 15), despite concerns about the tendency those gendered and racialized features are conducive to specific kinds of user…”
History and Development Tendency of Human - Computer Dialogue System
Lin, X., Yuan, T., & Lei, G. (2019) · International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd.2019.8836978 · Cited by 1
“These IPAs are typically deployed on mobile devices [15].”
BackgroundEngaging Communities in Public Safety via Social Media
Chaudhry, S. B., & Yüksel, M. (2019) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infcomw.2019.8845232 · Cited by 1
“Today’s social chatbots can have an engaging conversation with the user and gain the user’s trust through empathetic exchange [17].”
BackgroundEnd-to-end response selection based on multi-level context response matching
Boussaha, B. E. A., Hernández, N., Jacquin, C., & Morin, E. (2020) · Computer Speech & Language · doi:10.1016/j.csl.2020.101080 · Cited by 1
Svikhnushina, E., & Pu, P. (2020) · Cited by 1
Attention and Graph Matching Network for Retrieval-Based Dialogue System with Domain Knowledge
Li, X., & Zhu, J. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207347 · Cited by 1
“By contrast, retrieval-based dialogue systems are superior to generative dialogue systems because they can generate coherent and syntactically responses and they have mature industry products such as social bot XiaoIce from Microsoft [7].”
BackgroundImplementierung digitaler Prozesse
Woratschek, H., Borgdorf, U., Dornbusch, D., Finken, T., Große, C., Haefs, R., Knocke, H., Stopa, P., Vollmer, M., Wilhelm, J. B., et al. (2020) · Springer eBooks · doi:10.1007/978-3-658-30484-3_2 · Cited by 1
User Story Driven Adaptive Planning Framework in Personal Daily Context
Li, Y., Shibata, H., & Takama, Y. (2020) · International Symposium on Community-centric Systems (CcS) · doi:10.1109/ccs49175.2020.9231325 · Cited by 1
“While iterating the processes, bottleneck remind and sprint retrospective play a role as a proactive assistance [9].”
BackgroundMethodInfluentialIntra-/Inter-Interaction Network with Latent Interaction Modeling for Multi-turn Response Selection
Deng, Y., Zhang, W., & Lam, W. P. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.437 · Cited by 1
“Recent years have witnessed many successful real-world applications on chatbots and AI assistants, such as the XiaoIce (Shum et al., 2018) from Microsoft and the E-commerce assistant AliMe (Li et al., 2017) from Alibaba Group, which owe to the extensive researches on dialogue systems.”
BackgroundRole-Aware Enhanced Matching Network for Multi-turn Response Selection in Customer Service Chatbots
Zhao, G., Zhu, Y. N., Feng, S., Wang, D., Zhang, Y., & Yu, G. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-65390-3_49 · Cited by 1
Kreative Künstliche Intelligenz und Emotionen
Paaß, G., & Hecker, D. (2020) · Künstliche Intelligenz · doi:10.1007/978-3-658-30211-5_9 · Cited by 1
Anti-Drug Buddy: A Chatbot for Advocating the Awareness of Anti-Drug
Chen, L.-H., Wu, E. H., Yang, C.-C., Gao, T., & Tang, L.-H. (2022) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-96451-1_18 · Cited by 1
Maschinelles Lernen zur Förderung von höheren Kompetenzen
Giang, C., Wambsganß, T., & Käser, T. (2022) · Lernen und Lernstörungen · doi:10.1024/2235-0977/a000393 · Cited by 2
Samsonovich, A. V., Liu, Z., & Liu, T. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-19907-3_36 · Cited by 1
Evolution of Chatbots and their Demand Prospects on E-commerce in India
Singh, P., & Yadav, M. (2022) · Splint International Journal Of Professionals · doi:10.5958/2583-3561.2022.00026.1 · Cited by 1
Liang, J., Liu, C., Tao, C., Feng, J., & Zhao, D. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.422 · Cited by 2
“Since retrieval-based methods can usually provide fluent and informative responses, they are widely adopted in a variety of industrial applications such as XiaoIce (Shum et al., 2018) from Microsoft and AliMe Assist (Li et al., 2017) from Alibaba.”
MethodRead, Attend and Comment: A Deep Architecture for Automatic News Comment GenerationPreprint
Yang, Z., Xu, C., Wu, W., & Li, Z. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.11974 · Cited by 6
“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).”
BackgroundMulti-turn Dialogue Reading Comprehension with Pivot Turns and KnowledgePreprint
Zhang, Z., Li, J., & Zhao, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.05474 · Cited by 1
“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].”
BackgroundTowards humanized open-domain conversational agents
Zhong, P. (2021) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/147791 · Cited by 2
Conversational Agents in Software Engineering: Survey, Taxonomy and ChallengesPreprint
Motger, Q., Franch, X., & Marco, J. (2021) · arXiv (Cornell University) · Cited by 1
Building an Efficient and Effective Retrieval-based Dialogue System via Mutual LearningPreprint
Tao, C., Feng, J., Liu, C., Li, J., Geng, X., & Jiang, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.00159 · Cited by 8
“In this paper, we focus on retrieval-based dialogue systems as they can return fluent and informative responses (Tao et al. 2019) and have powered industrial applications such as the social chatbot Microsoft XiaoIce (Shum, He, and Li 2018) and the virtual assistant Amazon Alexa (Ram et al. 2018).”
Learning Neural Templates for Recommender Dialogue SystemPreprint
Liang, Z., Hu, H., Xu, C., Miao, J., He, Y., Chen, Y., Geng, X., Liang, F., & Jiang, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.12302 · Cited by 7
“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.”
Escrivá, J. V. S. (2021) · Tesis Doctorals en Xarxa (Consorci de Serveis Universitaris de Catalunya) · doi:10.6035/14111.2021.301397 · Cited by 6
Karaarslan, E., Alan, A. Y., Kumbalı, S., & Aydın, Ö. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4789423 · Cited by 1
Huang, J. (2024) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/175025 · Cited by 2
A Systematic Literature Review and Multi-Stakeholder Ethical Framework for Social ChatbotsPreprint
Piispanen, J.-R., Myllyviita, T., Vakkuri, V., & Rousi, R. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5220728 · Cited by 1
Generative AI as Mentors for International StudentsPreprint
Bayati, N. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5145535 · Cited by 2
IT-Entwicklungen für Innovationen nutzen
Grigoleit, S. (2018) · Innovative Verwaltung/VOP. Verwaltung, Organisation, Personal · doi:10.1007/s35114-018-0108-9
Incorporating Relevant Knowledge in Context Modeling and Response GenerationPreprint
Li, Y., Li, W., Cao, Z., & Chen, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.03729 · Cited by 1
“Rather, they are designed to engage and company users by chit-chat conversations (Shum, He, and Li 2018).”
BackgroundMemory-Based Model with Multiple Attentions for Multi-turn Response Selection
Lu, X., Lan, M., & Wu, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04179-3_26
Question-type Driven Question GenerationPreprint
Zhou, W., Zhang, M., & Wu, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.00140 · Cited by 3
“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.”
BackgroundBuilding A User-Centric and Content-Driven SocialbotPreprint
Fang, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.02623 · Cited by 1
“It has broad exposure in the Asian market with over 100 million users and billions of conversation turns [7].”
BackgroundSequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based ChatbotsPreprint
Xiong, C., Liu, C., Xu, Z., Jiang, J., & Ye, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.07923
“Therefore, retrieval-based approaches have been widely used in the industry such as the E-commerce assistant AliMe (Li et al., 2017) serving on Taobao1 and the XiaoIce (Shum et al., 2018) implemented by Microsoft 2.”
Wu, X., Jiang, N., & Wu, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.11665
“QG can also act as an essential component of other comprehensive task, such as dialogue systems (Piwek et al., 2007; Shum et al., 2018).”
BackgroundUsnea: An Authorship Tool for Interactive Fiction using Retrieval Based Semantic Parsing
Swanson, B., & Smus, B. (2020) · Annual Meeting of the Association for Computational Linguistics: System Demonstrations (ACL Demo) · doi:10.18653/v1/2020.acl-demos.29
“A typical dialog system design consists of components responsible for Language Understanding, Dialog Management, and Language Generation (Bohus and Rudnicky, 2009) (Shum et al., 2018).”
BackgroundShankar, S., Sruthi, V., Satyanarayana, V., & Das, B. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-3514-7_21
Wang, H., Li, M., Zhou, Z., Fung, G. P. C., & Wong, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.08772
“Task-oriented dialogue system attracts more attention since the application of virtual assistant Apple’s Siri 1 , Microsoft’s Cortana 2 and XiaoIce(Zhou et al., 2018) 3 , Google Assistant 4 , and Amazon’s Alexa 5 (Shum et al., 2018).”
BackgroundMining software support tickets for assistive routing
Han, J. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/143908 · Cited by 1
NICE: Neural Image Commenting Evaluation with an Emphasis on Emotion and Empathy
Chen, K., Huang, Q., McDuff, D., Wang, J., Palangi, H., Gao, X., Li, K., Forbus, K. D., & Gao, J. (2020)
A deep learning architecture for emotional aware chatbots
Grouls, R. H. (2020) · Utrecht University Repository (Utrecht University)
Designing Conversational Agents to Encourage User Narrative and Self-Reflection in Mental Wellbeing
Park, S. H. (2020) · Seoul National University Open Repository (Seoul National University) · Cited by 4
Conversational Query Rewriting with Self-supervised LearningPreprint
Liu, H., Chen, M., Wu, Y., He, X., & Zhou, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.04708
“Building conversational bots has attracted increasing attention due to the promising potentials on applications like virtual assistants [1] or customer service systems [2].”
BackgroundSelf-citationAn Emotion-controlled Dialog Response Generation Model with Dynamic VocabularyPreprint
Song, S., Wang, K., Wang, C., Chen, H., & Chen, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02878 · Cited by 3
Incorporating Background Knowledge into Dialogue Generation Using Multi-task Transformer Learning
Yuan, Y., & Cai, X. (2021) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd49262.2021.9437872
“One of the fundamental challenges in artificial intelligence (AI) is endowing the machine with the ability to converse with humans using natural language [1].”
BackgroundHernández-Carvajal, E. A., & Gómez–Ramírez, D. A. J. (2021) · Studies in systems, decision and control · doi:10.1007/978-3-030-69744-0_27
Personalized Response Generation with Tensor Factorization
Wang, Z., Luo, L., & Yang, D. (2021) · Workshop on Generation, Evaluation and Metrics (GEM) · doi:10.18653/v1/2021.gem-1.5 · Cited by 2
“…conversational systems has received much attention in artificial intelligence communities, and personalized response generation is one essential step towards this goal, as more personalized responses are often associated with increased user engagement (Shum et al., 2018; Huang et al., 2020).”
BackgroundMulti -Turn Response Selection with Temporal Gated Graph Convolutional Networks
Tao, S., Zhao, Q., Wang, L., & He, L. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534300
“However, several studies have shown that existing chatbot engines rely heavily on linguistic information matching for response selection [2], causing a great many logically incorrect responses [3].”
BackgroundStylistic Retrieval-based Dialogue System with Unparallel Training DataPreprint
Fu, H., Wang, Y., Song, R., Hu, T., & Nie, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.05477 · Cited by 1
“…conversation context and response candidates for response selection (Yan et al.2016; Wu et al.2017; Zhou et al.2018b; Zhang et al.2018b; Tao et al.2019) Such systems generally produce more fluent and diverse responses and are widely used in commercial chat-bots (Shum, He, and Li 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.