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 201–300 of 746
Kuhail, M. A., Bahja, M., Al-Shamaileh, O., Thomas, J., Alkazemi, A., & Negreiros, J. G. M. (2024) · IEEE Access · doi:10.1109/access.2024.3402977 · Cited by 36
“Given its critical role in fostering positive user experiences, chatbot designers must prioritize strategies to enhance engagement [50].”
BackgroundConversational Agents: Acting on the Wave of Research and Development
Jacques, R., Følstad, A., Gerber, E. M., Grudin, J. T., Luger, E. A., Monroy‐Hernández, A., & Wang, D. (2019) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3290607.3299034 · Cited by 23
“Xiaoice [19] is a quirky hip chatbot with hundreds of millions of users and a family of siblings; Hugging Face specializes in recognizing the mood of a human conversational partner.”
BackgroundWang, H., Wu, Z., & Chen, J. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3357928 · Cited by 21
How Virtual Personal Assistants Influence Children’s Communication
Bylieva, D. S., Bekiroğulları, Z., Lobatyuk, V. V., & Nam, T. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-65857-1_12 · Cited by 27
Unstructured Text Enhanced Open-Domain Dialogue System: A Systematic Survey
Ma, L., Li, M., Zhang, W., Li, J., & Liu, T. (2021) · ACM Transactions on Information Systems · doi:10.1145/3464377 · Cited by 30
Antonie, N. I., Gheorghe, G., Ionescu, V. A., Tiucă, L.-C., & Diaconu, C. C. (2025) · Antibiotics · doi:10.3390/antibiotics14010060 · Cited by 28
“Building on foundational research in conversational artificial intelligence dating back to 1966, these systems demonstrate significant potential as continuous advancements enhance their capabilities and broaden their applications [40–42].”
Diverse dialogue generation by fusing mutual persona-aware and self-transferrer
Xu, F., Xu, G., Wang, Y., Wang, R., Ding, Q., Liu, P., & Zhu, Z. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02660-4 · Cited by 25
Ontology-based Integration of Knowledge Base for Building an Intelligent Searching Chatbot
Nguyen, H. D., Tran, T.-V., Pham, X.-T., Huynh, A. T., & Do, N. V. (2021) · Sensors and Materials · doi:10.18494/sam.2021.3264 · Cited by 29
COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas
Xu, C., Li, P., Wang, W., Yang, H., Wang, S., & Xiao, C. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531957 · Cited by 48
2018 special issue on artificial intelligence 2.0: theories and applications
Pan, Y. (2018) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1810000 · Cited by 20
Abedi, M., Alshybani, I., Shahadat, M., & Murillo, M. S. (2023) · Qeios · doi:10.32388/md04b0.2 · Cited by 24
Assessing AI Adoption and Digitalization in SMEs: A Framework for ImplementationPreprint
Proietti, S., & Magnani, R. (2025) · Qeios · doi:10.32388/0n53p4 · Cited by 20
Wu, Y., He, K., Yan, Y., Gao, Q., Zeng, Z., Zheng, F., Zhao, L., Jiang, H., Wu, W., & Xu, W. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.307 · Cited by 19
“Out-of-domain (OOD) detection is a key component of the task-oriented dialogue system(Gnewuch et al., 2017; Akasaki and Kaji, 2017; Shum et al., 2018; Tulshan and Dhage, 2019).”
Backgroundde Azevedo, N. D. S., Aquino, G., Nascimento, L., Camelo, L., Figueira, T., Oliveira, J. P. D., Figueiredo, I. S. G., Printes, A. L., Torné, I. G., & Figueiredo, C. M. S. (2023) · Applied Sciences · doi:10.3390/app13116777 · Cited by 33
A Dataset for Low-Resource Stylized Sequence-to-Sequence Generation
Wu, Y., Wang, Y., & Liu, S. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6468 · Cited by 21
“However, a surge of tasks require S2S models to generate texts in a specific style without abundant parallel data, such as formal response generation in chatbots, which is in high demand but does not perform very well (Shum, He, and Li 2018).”
MethodGunrock 2.0: A User Adaptive Social Conversational SystemPreprint
Liang, K.-H., Chau, A., Li, Y., Lu, X., Yu, D., Zhou, M., Jain, I., Davidson, S. R., Arnold, J., Nguyen, M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.08906 · Cited by 37
Comparing supervised and unsupervised approaches to multimodal emotion recognition
Carbonell, M. F., Boman, M., & Laukka, P. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.804 · Cited by 22
Development of Intelligent Telegram Chatbot Using Natural Language Processing
Gunawan, T. S., Balla, A., Ismail, N., & Effendi, M. R. (2021) · International Conference on Wireless and Telematics (ICWT) · doi:10.1109/icwt52862.2021.9678471 · Cited by 25
Faisal, M. N., Subaie, A. A. A., Sabir, L. B., & Sharif, K. J. (2022) · Benchmarking An International Journal · doi:10.1108/bij-10-2021-0583 · Cited by 18
PEDM: A Multi-task Learning Model for Persona-aware Emoji-embedded Dialogue Generation
Zhao, S., Jiang, H., Tao, H., Zha, R., Zhang, K., Xu, T., & Chen, E. (2022) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3571819 · Cited by 23
“Some studies [33, 48] have explored further allowing chatbots to respond with visual elements.”
BackgroundYin, R., & Neyens, D. M. (2023) · Patient Education and Counseling · doi:10.1016/j.pec.2023.108055 · Cited by 19
Babić, S., Orehovački, T., & Etinger, D. (2018) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.23919/mipro.2018.8400153 · Cited by 21
Toward Design Archetypes for Conversational Agent Personality
Lessio, N., & Morris, A. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9283254 · Cited by 28
“As the landscape of conversational agents continues to evolve into platforms such as smart speakers, mobile devices, people’s private homes, and even vehicles, there has been a renewed interest in adapting them to help solve many different kinds of challenges [2].”
BackgroundMethodInfluentialFirdaus, M., Thangavelu, N., Ekbal, A., & Bhattacharyya, P. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3155105 · Cited by 30
How to Evaluate Health Applications with Conversational User Interface?
Kerstin, D., & Jim, W. (2020) · Studies in Health Technology and Informatics · doi:10.3233/shti200307 · Cited by 18
Cultivating Gratitude with a Chatbot
Lee, M., Alejandro, J. C., & IJsselsteijn, W. A. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2231277 · Cited by 23
“…for conversational agents to be more than simple systems, tools, or digital assistants for practical tasks (Brandtzaeg & Følstad, 2017; Clark et al., 2019; Dale, 2016; Shum et al., 2018) while holding two roles as a mediator of human-human gratitude and a beneficiary of human gratitude towards it.”
AI teachers (AI-based robots as teachers): history, potential, concerns and recommendations
Malik, M. A., & Shah, R. (2025) · Frontiers in Education · doi:10.3389/feduc.2025.1541543 · Cited by 23
“ELIZA, developed by MIT in the 1960s, was the first chatbot that employed AI (Berry, 2023; Shum et al., 2018).”
Emotive Expressions on Social Chatbot
Indrayani, L. M., Amalia, R. M., & Hakim, F. Z. M. (2020) · Jurnal Sosioteknologi · doi:10.5614/sostek.itbj.2019.18.3.17 · Cited by 17
Petousi, D., Katifori, A., McKinney, S., Perry, S., Roussou, M., & Ioannidis, Y. (2021) · ACM International Conference on Interaction Design and Children (IDC) · doi:10.1145/3459990.3460710 · Cited by 17
“The fundamental mechanism of human level intelligence, frequently reflected in human to human communication, is not yet fully understood [12].”
BackgroundLi, J., Meng, Y., Wu, X., Wu, Z., Jia, J., Meng, H. M. L., Tian, Q., Wang, Y., & Wang, Y. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547831 · Cited by 24
“With the development of deep learning and speech processing technologies [13, 25–27, 30, 37], speech-driven interactive systems, such as virtual assistants and voice agents are becoming increasingly pervasive in real-world applications [9, 20, 33, 42] which present a diversity of conversational scenarios.”
BackgroundHumanizing Chatbots for Interactive Marketing
Tsai, W. S., & Chuan, C. (2023) · Springer eBooks · doi:10.1007/978-3-031-14961-0_12 · Cited by 22
Choi, Y. J., Lee, M., & Lee, S. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581445 · Cited by 39
“Thus, conversational agents are designed to imitate various human linguistic and behavioral patterns [102], including the languagemixing patterns of multilingual users.”
BackgroundQiu, L., Shiu, Y., Lin, P., Song, R., Liu, Y., Zhao, D., & Yan, R. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401108 · Cited by 25
“Compared with generation-based methods, retrieval-based models are superior in terms of response fluency, diversity, and efficiency, and thus have been widely applied in real-world products, such as Microsoft XiaoIce [29].”
BackgroundMethodContent Selection Network for Document-Grounded Retrieval-Based Chatbots
Zhu, Y., Nie, J., Zhou, K., Du, P., & Dou, Z. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72113-8_50 · Cited by 24
Xu, S., Li, H., Yuan, P., Wang, Y., Wu, Y., He, X., Liu, Y., & Zhou, B. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.1 · Cited by 26
Self-citationSEQ2SEQ++: A Multitasking-Based Seq2seq Model to Generate Meaningful and Relevant Answers
Palasundram, K., Sharef, N. M., Kasmiran, K. A., & Azman, A. (2021) · IEEE Access · doi:10.1109/access.2021.3133495 · Cited by 18
“Chatbots can be broadly categorized into two types, namely transactional and conversational [3], [4].”
BackgroundLin, J.-S. (2024) · International Journal of Advertising · doi:10.1080/02650487.2024.2410559 · Cited by 26
Suryanto, T. L. M., Wibawa, A. P., Hariyono, H., & Nafalski, A. (2023) · International Journal of Robotics and Control Systems · doi:10.31763/ijrcs.v3i4.1195 · Cited by 34
Esmaeilzadeh, P., Hassanein, K., & Head, M. M. (2025) · Behaviour and Information Technology · doi:10.1080/0144929x.2025.2477754 · Cited by 21
Chatbot or Chat-Blocker: Predicting Chatbot Popularity before Deployment
Gao, M., Liu, X., Xu, A., & Akkiraju, R. (2021) · Designing Interactive Systems Conference · doi:10.1145/3461778.3462147 · Cited by 19
“In addition, chatbots have a long history of being used as virtual companions starting from the pioneering social chatbot, ElIZA [50] to the current Microsoft Xiaoice [45].”
BackgroundAutomated information retrieval and services of graduate school using chatbot system
Rukhiran, M., & Netinant, P. (2022) · International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering · doi:10.11591/ijece.v12i5.pp5330-5338 · Cited by 20
“The online chatbot system can implement supporting the internet of things (IoT) [20].”
DEVELOPMENT OF A QUESTION ANSWERING CHATBOT FOR BLOCKCHAIN DOMAIN
Mansurova, A., Nugumanova, A., & Makhambetova, Z. (2023) · Scientific Journal of Astana IT University · doi:10.37943/15xndz6667 · Cited by 28
“The earliest known chat - bot, Eliza, was created in 1966 with the goal of functioning as a psychotherapist, responding to user inputs with questions [8].”
BackgroundThe Influence of Generative AI on Interpersonal Communication Dynamics
Akdilek, S., Akdilek, I., & Punyanunt-Carter, N. M. (2024) · Advances in educational technologies and instructional design book series · doi:10.4018/979-8-3693-0831-8.ch009 · Cited by 21
Conversational AI and Chatbots: Enhancing User Experience on Websites
Dobbala, M. K., & Lingolu, M. S. S. (2024) · American Journal of Computer Science and Technology · doi:10.11648/j.ajcst.20240703.11 · Cited by 17
A Hierarchical Structured Multi-Head Attention Network for Multi-Turn Response Generation
Lin, F., Zhang, C., Liu, S., & Ma, H. (2020) · IEEE Access · doi:10.1109/access.2020.2977471 · Cited by 15
“As a fundamental challenge in artificial intelligence, conversation systems aim to give machines the ability to communicate with humans using natural language [1].”
BackgroundPersona aware Response Generation with Emotions
Firdaus, M., Thangavelu, N., Ekba, A., & Bhattacharyya, P. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207529 · Cited by 19
“This helps in making the conversation interactive and also facilitates building user’s trust and confidence [9].”
BackgroundStyleDGPT: Stylized Response Generation with Pre-trained Language Models
Yang, Z., Wu, W., Xu, C., Liang, X., Bai, J., Wang, L., Wang, W., & Li, Z. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.140 · Cited by 30
The Use Of Chat-Bot Capabilities As A Type Of Modeling In Intelligent Learning
Kerimbayev, N., Jotsov, V., Umirzakova, Z., Bolyskhanova, M., & Tkach, G. (2022) · IEEE International Conference on Intelligent Systems · doi:10.1109/is57118.2022.10019627 · Cited by 18
“As we become the first generation of humans ever to live with artificial intelligence (AI), it is our responsibility to design social chatbots to be useful and responsive, so that they become everyday-life and help society at large [19].”
BackgroundFeng, J., Tao, C., Zhao, X., & Zhao, D. (2023) · ACM Transactions on Information Systems · doi:10.1145/3584701 · Cited by 18
“Retrieval-based approaches are superior in terms of response luency and diversity, and have been widely applied in commercial chatbots such as the social bot XiaoIce [35] from Microsoft, and the E-commerce assistant AliMe from Alibaba [19].”
MethodDeep Retrieval-Based Dialogue Systems: A Short ReviewPreprint
Boussaha, B. E. A., Hernández, N., Jacquin, C., & Morin, E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12878 · Cited by 22
“In this work, we are interested in studying retrieval-based dialogue systems as they have proved their efficiency in both academia and industry products such as the Alibaba’s chatbot AliMe (Qiu et al., 2017) and the Microsoft’s socialbot XiaoIce1 (Shum et al., 2018).”
Cuadra, A., Baek, H., Estrin, D., Jung, M., & Dell, N. (2022) · International Conference on Information & Communication Technologies and Development 2022 · doi:10.1145/3572334.3572371 · Cited by 16
The evolution of language models: From N-Grams to LLMs, and beyond
Raeini, M. (2025) · Natural Language Processing Journal · doi:10.1016/j.nlp.2025.100168 · Cited by 40
Siemon, D., Ahmad, R., Harms, H., & de Vreede, T. (2022) · Sustainability · doi:10.3390/su14073832 · Cited by 16
“While PARRY passed the Turing test for the first time in history, it was still a rule-based CA and had a similar functioning as ELIZA, though with better language understanding capabilities [25].”
BackgroundMethodShan, Y., Ji, M., Xie, W., Zhang, X., Qian, X., Li, R., & Hao, T. (2022) · JMIR Human Factors · doi:10.2196/36831 · Cited by 20
“They believed that the selected chatbots could fully engage them when they communicated with the chatbots for self-diagnosis and acquisition of general information concerning COVID-19 and the latest virus variants, thus satisfying their needs for communication, affection, and social belonging [69].”
BackgroundInfluentialHistory-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System
Zhang, T., Liu, Y., Li, B., Zeng, Z., Wang, P., You, Y., Miao, C., & Cui, L. (2022) · Findings of the Association for Computational Linguistics: EMNLP 2022 · doi:10.18653/v1/2022.findings-emnlp.247 · Cited by 14
Who has the last word? Lessons from using ChatGPT to develop an AI-based Spanish writing assistant
Tarp, S., & Rull, A. N. (2024) · Círculo de lingüística aplicada a la comunicación · doi:10.5209/clac.91985 · Cited by 14
Talk2Learn: A Framework for Chatbot Learning
Bahja, M., Hammad, R., & Hassouna, M. S. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29736-7_44 · Cited by 19
Enhancing the Perceived Emotional Intelligence of Conversational Agents through Acoustic Cues
Hu, J., Huang, Y., Hu, X., & Xu, Y. (2021) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3411763.3451660 · Cited by 16
“Agents are usually embedded with machine learning models to detect user’s emotions from text input [13, 14, 33].”
BackgroundMethodIntroducing the v-RFA, a voice assistant-based geriatric assessment
Cuadra, A., Chen, Y., Cho, K.-J., Estrin, D. L., & Shahrokni, A. (2022) · Journal of Geriatric Oncology · doi:10.1016/j.jgo.2022.05.001 · Cited by 14
Kim, H., Jung, I., & Lim, Y.-K. (2022) · Designing Interactive Systems Conference · doi:10.1145/3532106.3533528 · Cited by 22
“typically aims to imitate humans or continue conversations for as many exchanges as possible [58], conversational agents’ autonomy may be increased indiscriminately.”
BackgroundNeural Topic Modeling of Psychotherapy Sessions
Lin, B., Bouneffouf, D., Cecchi, G., & Tejwani, R. (2023) · Studies in computational intelligence · doi:10.1007/978-3-031-36938-4_16 · Cited by 14
MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions
Sun, H., Zhang, Z., Mi, F., Wang, Y., Liu, W., Cui, J., Wang, B., Liu, Q., & Huang, M. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.123 · Cited by 39
“As an important application of AI, open-domain dialogue systems, which directly interact with users, requires the nature of morality more urgently (Shum et al., 2018; Qiu et al., 2021).”
BackgroundState Audit Bureau (SAB), K., Al-Ebrahim, M. A., Bunian, S., & Nour, A. A. (2023) · Engineered Science · doi:10.30919/es1044 · Cited by 40
Garg, A., Gupta, S., Vats, S., Handa, P., & Goel, N. (2024) · Expert Systems · doi:10.1111/exsy.13697 · Cited by 16
Shankar, R., Bundele, A., Yap, A. E., & Mukhopadhyay, A. (2025) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2025.1553494 · Cited by 16
A unified scheme of text localization and structured data extraction for joint OCR and data mining
Ye, Y., Zhu, S., Wang, J., Du, Q., Yang, Y., Tu, D., Wang, L., & Luo, J. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622129 · Cited by 20
“input : Pyramid levels L = [3, 4, 5, 6, 7] output: An array of anchors A Initialize an empty array A to store anchors; foreach pyramid level l ∈ L do Choose a set of independent anchor heights Hl (perferably within [2, 2]) ; Choose a set of independent aspect ratios Rl (e.”
BackgroundCognitive checkpoint: Emerging technologies for biometric-enabled watchlist screening
Yanushkevich, S. N., Sundberg, K. W., Twyman, N. W., Guest, R., & Shmerko, V. P. (2019) · Computers & Security · doi:10.1016/j.cose.2019.05.002 · Cited by 16
“From the taxonomical view point, e-interviewer is a particular kind of spoken dialog-machines, or chatbots (also known as chat-agents), such as Clever-bot, XiaoIce, and Alice [55], [75].”
BackgroundDeepRouting: A Deep Neural Network Approach for Ticket Routing in Expert Network
Han, J., & Sun, A. (2020) · IEEE International Conference on Services Computing · doi:10.1109/scc49832.2020.00057 · Cited by 16
“DSSM and its variations are widely adopted models for many text matching applications, such as information retrieval [13], [14], [15], recommendation [16], [17], [24], [25], and chatbot [26], [27].”
BackgroundZeng, H., Zhi, Z., Liu, J., & Wei, B. (2021) · Information Sciences · doi:10.1016/j.ins.2021.04.026 · Cited by 15
Reinforcement Learning for Personalized Dialogue Management
den Hengst, F., Hoogendoorn, M., van Harmelen, F., & Bosman, J. (2019) · IEEE/WIC/ACM International Conference on Web Intelligence · doi:10.1145/3350546.3352501 · Cited by 26
“query to the items in X. The DM policy is handcrafted, which typically entails many nontrivial decisions that can seriously impact system performance [16]. More recent examples, such as [14], [3] and [27] collect user-related facts in a knowledge graph. These facts are 2 then used to personalize hand-crafted response…”
Background“Always on the Table”: Revealing Smartphone Usages in everyday Eating Out Situations
Weber, P. P., Engelbutzeder, P., & Ludwig, T. G. (2020) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3419249.3420150 · Cited by 15
“…disturbing at first, and people’s acceptance of anthropomorphized chatbots and robots is still difficult to assess [36, 81], but prototypes such as the companion robot FoBo [45] and the successes of social chatbots, including Rinna and XiaoIce [70], show that this approach is not to be neglected.”
BackgroundGenerating Diversified Comments via Reader-Aware Topic Modeling and Saliency Detection
Wang, W., Li, P., & Zheng, H.-T. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i16.17647 · Cited by 20
Adversarial Generative Distance-Based Classifier for Robust Out-of-Domain Detection
Zeng, Z., Xu, H., He, K., Yan, Y., Liu, S., Liu, Z., & Xu, W. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413908 · Cited by 15
“Task-oriented dialogue systems [1, 2, 3, 4, 5], such as Google’s DialogFlow or Amazon’s Lex, are ubiquitous, allowing people to interact with machines using natural language.”
BackgroundLanguage Style Transfer from Sentences with Arbitrary Unknown StylesPreprint
Zhao, Y., Bi, W., Cai, D., Liu, X., Tu, K., & Shi, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.04071 · Cited by 25
“However, existing chatbots such as Siri, Cortana, and XiaoIce (Shum et al., 2018) lack the ability of generating responses with a consistent persona during the whole conversation.”
BackgroundGuo, M., & Liu, Z. (2025) · Theory & Psychology · doi:10.1177/09593543251319738 · Cited by 12
“Chatbots are valued not only for their capacity to address inquiries or commands but also for their skill in forming emotional bonds with users (Chaturvedi et al., 2023; Shum et al., 2018).”
GRICE: A Grammar-based Dataset for Recovering Implicature and Conversational rEasoning
Zheng, Z., Qiu, S., Fan, L., Zhu, Y., & Zhu, S. C. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.182 · Cited by 47
“However, the inspiring progress was recently challenged by researchers (Shum et al., 2018; Young et al., 2018); there remain valid concerns that systems are simply imitating human responses by regressing a large amount of training data without truly understanding it.”
BackgroundConversational recommendation: A grand AI challenge
Jannach, D., & Chen, L. (2022) · AI Magazine · doi:10.1002/aaai.12059 · Cited by 29
Acer, U. G., den Broeck, M. V., Min, C., Dasari, M., & Kawsar, F. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3534573 · Cited by 14
“In recent literature, we have seen several studies addressing the social acceptance of conversational agents and interaction dynamics across different modalities [10, 16, 21, 46, 53, 55].”
BackgroundA Review of Conversational Agents in Education
Rodrigues, C., dos Reis, A. M., Pereira, R., Martins, P., Sousa, J., & Pinto, T. D. O. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-22918-3_37 · Cited by 16
Chu, T. H., & Jiang, L. (2023) · Computers in Human Behavior · doi:10.1016/j.chb.2023.108018 · Cited by 18
Processing Natural Language on Embedded Devices: How Well Do Transformer Models Perform?
Sarkar, S., Babar, M. F., Hassan, M. M., Hasan, M., & Karmaker, S. K. (2024) · ACM/SPEC International Conference on Performance Engineering (ICPE) · doi:10.1145/3629526.3645054 · Cited by 30
“Thus our empirical study is applicable in broader human-centric application domains, including chatbots [23–25], virtual assistants [26, 27], and language translation [28, 29].”
Countering Misinformation in Private Messaging Groups: Insights From a Fact-checking Chatbot
Lee, T.-H., & Fussell, S. R. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3701189 · Cited by 21
“Prior work has assigned various social roles, like friend [99], tutor [67] or expert [77], in designing human-agent interactions.”
Yu, Q., & Lan, X. (2024) · Proceedings of the Twelfth International Symposium of Chinese CHI · doi:10.1145/3758871.3758884 · Cited by 12
CORK: A COnversational agent framewoRK exploiting both rational and emotional intelligence.
Catania, F., Spitale, M., & Fisicaro, D. (2019) · Virtual Community of Pathological Anatomy (University of Castilla La Mancha) · Cited by 12
E-commerce Distributed Chatbot System
Angelov, S., & Lazarova, M. K. (2019) · Balkan Conference in Informatics · doi:10.1145/3351556.3351587 · Cited by 13
“Love Is as Complex as Math”: Metaphor Generation System for Social Chatbot
Zheng, D., Song, R., Hu, T., Fu, H., & Zhou, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-38189-9_36 · Cited by 12
“ches on task-oriented systems are mainly focusing on addressing users’ queries and generating informative answers. In recent years, more and more attention has been paid to non-task-oriented chatbots [17], which aim to hold casual and engaging conversations with users in open domains. A number of studies [7, 8] have b…”
BackgroundDeveloping a Twitter bot that can join a discussion using state-of-the-art architectures
Çetinkaya, Y. M., Toroslu, İ. H., & Davulcu, H. (2020) · Social Network Analysis and Mining · doi:10.1007/s13278-020-00665-4 · Cited by 20
“Microsoft’s chatbot XiaoIce has been designed as a 19-year-old female persona, with strong language ability, visual awareness, and over 180 skills (Shum et al. 2018).”
BackgroundMethodImproving the level of trust in human-machine conversation
Sucameli, I. (2021) · Advanced Robotics · doi:10.1080/01691864.2021.1884132 · Cited by 14
“It includes knowledge and memory modelling, image and language understanding, robustness to manipulation, and general ease of use [6].”
BackgroundMethodInfluentialIrfan, B., Hellou, M., & Belpaeme, T. (2021) · Frontiers in Robotics and AI · doi:10.3389/frobt.2021.676814 · Cited by 14
Learning to Ask Like a Physician
Lehman, E., Lialin, V., Legaspi, K. E., Sy, A. J., Pile, P. T., Alberto, N. R., Ragasa, R. R., Puyat, C. V., Taliño, M. K., Alberto, I. R., et al. (2022) · Proceedings of the 4th Clinical Natural Language Processing Workshop · doi:10.18653/v1/2022.clinicalnlp-1.8 · Cited by 10
Wei, Z., Chen, Y., Zhao, Q., Zhang, P., Zhou, L., Ren, J., Piao, Y., Qiu, B., Xie, X., Wang, S., et al. (2023) · Advanced Science · doi:10.1002/advs.202203990 · Cited by 13
Designing the Conversational Agent: Asking Follow-up Questions for Information Elicitation
Hu, J., Guo, J., Tang, N., Ma, X., Yao, Y., Yang, C., & Xu, Y. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637320 · Cited by 19
“CAs have demonstrated their abilities to collect information and serve as initiators of information elicitation tasks in public service [59], education [25, 26, 30, 63], and healthcare [40].”
BackgroundEmotion-Aware Chatbots: Understanding, Reacting and Adapting to Human Emotions in Text Conversations
Kossack, P., & Unger, H. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-61418-7_8 · Cited by 18
Jacobs, O. L. E., Pazhoohi, F., & Kingstone, A. F. (2024) · Consciousness and Cognition · doi:10.1016/j.concog.2024.103733 · Cited by 14
“While this interest harkens back to an earlier period with chatbots such as ELIZA (Weizenbaum, 1966; Shum et al., 2018), the immense technological developments and widespread popularity of LLMs have reinvigorated the need to understand attitudes toward AI systems.”
BackgroundAI-Powered Smart Digital Libraries
Meesad, P., & Mingkhwan, A. (2024) · Studies in big data · doi:10.1007/978-3-031-69216-1_10 · Cited by 20
Conversational User Interfaces and Agents
Biancofiore, G. M., Palma, D. D., Pomo, C., Narducci, F., & Noia, T. D. (2025) · Human-computer interaction series · doi:10.1007/978-3-031-61375-3_4 · Cited by 20
Relational AI: Facilitating Intergroup Cooperation with Socially Aware Conversational Support
Claggett, E. L., Kraut, R. E., & Shirado, H. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713757 · Cited by 29
“Given that conversation plays a central role in both cooperation and the development of social identity [88, 127], conversational AI — such as writing assistance systems and chatbots [117] — may provide a technical solution to the challenge of intergroup cooperation [10, 31, 68].”
COMPASS: Computational mapping of patient-therapist alliance strategies with language modeling
Lin, B., Bouneffouf, D., Landa, Y., Jespersen, R., Corcoran, C. M., & Cecchi, G. (2025) · Translational Psychiatry · doi:10.1038/s41398-025-03379-3 · Cited by 18
“Although psychotherapy was an early adopter of Natural Language Processing (NLP), with pioneering efforts like ELIZA and Parry simulating therapeutic interactions [18, 19], these innovations never gained systematic clinical adoption.”
Transparency in Language Generation
Edwards, J., Perrone, A., & Doyle, P. R. (2020) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3405755.3406136 · Cited by 11
“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.”
BackgroundHow Human Communication Influences Virtual Personal Assistants
Bylieva, D. S., Lobatyuk, V. V., Kuznetsov, D., & Anosova, N. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-65857-1_11 · Cited by 13
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.