Cited by 815Speech and dialogue systemsAI in Service InteractionsSocial Robot Interaction and HRI

The DOI matches its Crossref record; 73 of the 73 references it cites were found in a registry or an index; none of the 27 sources its claims cite is checked for support yet.

The Design and Implementation of XiaoIce, an Empathetic Social Chatbot

Open access

Zhou, Li, Gao, Jianfeng, Li, Di, Shum, Heung-Yeung·2020·Computational Linguistics

DOI 10.1162/coli_a_00368

Open this paper in CoChat — free account

Abstract

This article describes the development of Microsoft XiaoIce, the most popular social chatbot in the world. XiaoIce is uniquely designed as an artifical intelligence companion with an emotional connection to satisfy the human need for communication, affection, and social belonging. We take into account both intelligent quotient and emotional quotient in system design, cast human–machine social chat as decision-making over Markov Decision Processes, and optimize XiaoIce for long-term user engagement, measured in expected Conversation-turns Per Session (CPS). We detail the system architecture and key components, including dialogue manager, core chat, skills, and an empathetic computing module. We show how XiaoIce dynamically recognizes human feelings and states, understands user intent, and responds to user needs throughout long conversations. Since the release in 2014, XiaoIce has communicated with over 660 million active users and succeeded in establishing long-term relationships with many of them. Analysis of large-scale online logs shows that XiaoIce has achieved an average CPS of 23, which is significantly higher than that of other chatbots and even human conversations.

AI snapshot

Written from the paper’s full text.

TL;DR

This paper describes Microsoft XiaoIce, an empathetic social chatbot designed as an AI companion with IQ, EQ, and personality, optimized for long-term user engagement measured by expected Conversation-turns Per Session (CPS). It reports system architecture, dialogue manager, empathetic computing, Core Chat, skills, and large-scale deployment results, including 660 million active users and an average CPS of 23.

Key findings

XiaoIce was launched in May 2014 and by July 2018 had over 660 million active users, was deployed in five countries on more than 40 platforms, and achieved an average CPS of 23 in its 6th generation; the paper compares this with CPS 9 for human conversations in its user study and CPS 14.6 for the latest Amazon Alexa systems per Khatri et al. [2018].
The empathetic computing module’s A/B test on Weibo showed no significant CPS change but increased NAU from 0.5 million to 5.1 million in 3 months; it was released in July 2018 and became the most important feature in the 6th generation.
Core Chat’s hybrid approach improved expected CPS by 0.5 in two weeks over a retrieval-only baseline; incorporating the neural generator and unpaired-data retrieval improved response coverage by 20% and 10%, respectively. Topic Manager improved Core Chat expected CPS by 0.5, and Image Commenting doubled expected CPS across all dialogues containing images.
The persona-based neural response generator achieved perplexity 25.0 (−8.4% vs. seq2seq) and BLEU 1.9% (+18.8% vs. seq2seq, +11.8% vs. LSTM-MMI) on the TV series dataset; the XiaoIce Image Commenting prototype scored BLEU-4 4.53, ROUGE-L 15.33, CIDEr-D 3.21, METEOR 15.51, and SPICE 4.82, outperforming four state-of-the-art image captioning systems.

Methods

Design: XiaoIce is a modular system with user experience, conversation engine, and data layers; social chat is cast as hierarchical decision-making over options in Markov Decision Processes, with a dialogue manager, empathetic computing module, Core Chat, and 230 dialogue skills, optimized for expected CPS.
Data and training: paired conversational data included more than 30 billion conversation pairs as of May 2018, with 70% of XiaoIce’s responses retrieved from her own past conversations; classifiers for user understanding were trained on 10K manually labeled dialogue sessions, the response ranker on 50K manually labeled dialogues, neural generation and ranking features on 50 million human dialogues, and Image Commenting on 28 million images each paired with 6 text comments.
Evaluation: A/B tests used expected CPS and NAU; pilot studies used human ratings on a 3-level quality scale and benchmark metrics such as perplexity, BLEU, METEOR, CIDEr, ROUGE-L, and SPICE; large-scale online logs were analyzed over long periods.

Limitations

The paper states that automatic evaluation of open-domain dialogue systems is “by no means a solved problem,” that common automatic metrics have limitations, and that a unified modeling framework for XiaoIce “remains to be proved” effective.
The paper states that fully grounding all conversations in the physical world for goal-oriented interactions remains a non-trivial challenge, and that the fundamental mechanism of human-level intelligence is not yet fully understood.
The paper discusses ethical concerns including privacy, who is in control, unrealistic user expectations, and potential misuse; evident from the text, many key results come from proprietary A/B tests and online logs without reported confidence intervals or full statistical details, and the comparison to human conversations relies on an unspecified user study.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1162/coli_a_00368

Cites

73 of 73 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 27 cited sources checked · 0 supported · 0 flagged

The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Although the overall quality of the candidates generated from the unpaired database is lower than those retrieved from the paired database, with unpaired database XiaoIce can cover a much broader range of topics.”
Load-bearingStrength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
- Rests on an assumption: The unpaired database sentences from public lectures and quotes are suitable as candidate responses for XiaoIce.

Show all 73 claims

Probably not a substantial claim. 66
It may state two separate claims as one. 43
The quote only partly states this claim. 2

The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Since the release in 2014, XiaoIce has communicated with over 660 million active users and succeeded in establishing long-term relationships with many of them.”
- Also stated in: § 1 Introduction · p. 1 · plain
  “Since her launch in China in May 2014, XiaoIce has attracted over 660 million active users (i.e., subscribed users).”
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: fails
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
In the paper
“As shown in Table 1, the persona model significantly outperforms both baselines, achieving a lower perplexity (-8.4%) and a higher BLEU score (+18.8% and +11.8%) Papineni et al. [2002].”
What the sources say
- Not checked yetcites Papineni et al. [2002]
Load-bearingStrength:boosted· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one.
In the paper
“On May 15, 2018, XiaoIce published the first AI-created Chinese poem album in history 11 .”
What the sources say
- Not checked yetcites [11] Cuayáhuitl Heriberto, 2018
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“The dialogue policy is designed to optimize long-term user engagement through an iterative, trialand-error process based on the feedback of XiaoIce's users.”
Strength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: fails
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
- The authors state this as an assumption: Human-machine social chat can be modeled as a hierarchical decision-making process over Markov Decision Processes.
- The authors state this as an assumption: Expected CPS is a valid measure of long-term user engagement for social chatbots.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This paper describes the development of Microsoft XiaoIce , the most popular social chatbot in the world.”
- Also stated in: § 1 Introduction · p. 1 · plain
  “In this paper we present the design and implementation of Microsoft XiaoIce ('Little Ice' literally in Chinese), the most popular social chatbot in the world.”
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“More importantly, social chatbots also require a sufficient EQ to meet users' emotional needs, such as emotional affection and social belonging, which are among the fundamental needs for human beings Maslow [1943].”
What the sources say
- Not checked yetcites Maslow [1943]
Load-bearingStrength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Thus, XiaoIce has to interact with the user's environment and access real-world knowledge e.g., via API calls.”
Load-bearingStrength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one.
- Rests on an assumption: Traditionally, social chatbots are designed for chitchat scenarios where bots are expected to mimic human user conversations but not to interact with the user's environment.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“Each generated response is labeled on the 3-level quality scale by three human judges.”
Load-bearingStrength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
Probably not a substantial claim.
- Rests on an assumption: The 3-level quality scale labels assigned by human judges reliably measure response quality.
In the paper
“According to Khatri et al. [2018], the latest Alexa systems have achieved the CPS of 14.6, an increase of 54% since the launch of the 2018 competition.”
What the sources say
- Not checked yetcites Khatri et al. [2018]
Strength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
In the paper
“The second is the LSTM-MMI model Li et al. [2016a], which is one of the state-of-the-art neural response generation models.”
What the sources say
- Not checked yetcites Li et al. [2016a]
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Therefore, low BLEU (or other metrics) scores do not necessarily indicate low quality as the number of reference responses is always limited in the test set.”
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passes
It may state two separate claims as one. The quote only partly states this claim.
- Rests on an assumption: In open-domain dialog systems, the same input may have many plausible responses that differ in topics or contents significantly.
- Rests on an assumption: The number of reference responses in the test set is always limited.
In the paper
“Galley et al. [2015] showed that the correlation of string-based metrics (e.g., BLEU and deltaBLEU) significantly increases with the units of measurement bigger than a sentence.”
What the sources say
- Not checked yetcites Galley et al. [2015]
Strength:boosted· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“But as pointed out in Gao et al. [2019], the correlation analysis by Liu et al. [2016] is performed at the sentence level while BLEU is designed from the outset to be used as a corpus-level metric.”
What the sources say
- Not checked yetcites Gao et al. [2019]
- Not checked yetcites Liu et al. [2016]
Load-bearingStrength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
It may state two separate claims as one.
In the paper
“Retrieval-based methods are often evaluated using traditional information retrieval metrics Manning et al. [2008] such as as Precision@K, Mean Average Precision (MAP), and normalized Discounted Cumulative Gain (nDCG).”
What the sources say
- Not checked yetcites Manning et al. [2008]
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It is not surprising, then, that with vastly more people being digitally connected in the social media age, social chatbots have become an important alternative means for engagement.”
Strength:plain· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✗ Based: fails
Probably not a substantial claim. The paper’s conclusions may not depend on it. The paper may give no reason why it holds.
- Rests on an assumption: Happiness and meaningful conversations often go hand in hand.
None of the sources cited for this claim have been checked yet.
In the paper
“Generation-based methods are evaluated using those metrics borrowed from text generation tasks like machine translation and text summarization, using string and n-gram matching metrics such as BLEU Papineni et al. [2002], METEOR Banerjee and Lavie [2005] and ROUGE Lin [2004].”
What the sources say
- Not checked yetcites Papineni et al. [2002]
- Not checked yetcites Banerjee and Lavie [2005]
- Not checked yetcites Lin [2004]
Strength:plain· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
None of the sources cited for this claim have been checked yet.
In the paper
“However, as argued by Gao et al. [2019], machine-learned metrics lead to potential problems such as overfitting and 'gaming of the metric' Albrecht and Hwa [2007].”
What the sources say
- Not checked yetcites Gao et al. [2019]
- Not checked yetcites Albrecht and Hwa [2007]
Strength:hedged· not yet calibratedCausal:direct· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“deltaBLEU Galley et al. [2015] is an extension to BLEU that exploits numerical ratings associated with conversational responses.”
What the sources say
- Not checked yetcites Galley et al. [2015]
Strength:plain· not yet calibratedCausal:correlational· not yet calibrated
Tests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passes
Probably not a substantial claim. The paper’s conclusions may not depend on it.

89 of 89

The authors state this as an assumption.
Human-machine social chat can be modeled as a hierarchical decision-making process over Markov Decision Processes.
“we mathematically cast human-machine social chat as a hierarchical decision-making process, and optimize XiaoIce for long-term user engagement, measured in expected CPS.”
“cast human-machine social chat as decision-making over Markov Decision Processes (MDPs)”
The authors state this as an assumption.
Expected CPS is a valid measure of long-term user engagement for social chatbots.
“we propose to use expected Conversation-turns Per Session (CPS) as the success metric for social chatbots.”
“The larger the CPS is, the better engaged the social chatbot is.”
The paper relies on this without support.
An AI companion can satisfy the human need for communication, affection, and social belonging.
“XiaoIce is uniquely designed as an AI companion with an emotional connection to satisfy the human need for communication, affection, and social belonging.”
The paper relies on this without support.
The machine learning classifiers used for user understanding accurately detect user intents, emotions, topics, opinions, and persona from dialogue.
“These key-value pairs are generated using a set of machine learning classifiers as follows.”
The paper relies on this without support.
The TV series dataset used in the first pilot study is representative enough to validate the persona-based neural response generator for XiaoIce.
“In the first pilot study reported in Li et al. [2016b], we compare the persona model against two baseline models, using the TV series dataset for model training and evaluation.”
The paper relies on this without support.
The 3-level quality scale labels assigned by human judges reliably measure response quality.
“Each generated response is labeled on the 3-level quality scale by three human judges.”
The paper relies on this without support.
The KG triples that co-occur often in the same conversations represent related topics humans often discuss.
“We include in the XiaoIce KG a Satori triple ( h, r, t ) only if h and t co-occur often enough in the same conversations. Such a triple contains a pair of related topics ( h, t ) that humans often discuss in one conversation”
The paper relies on this without support.
The unpaired database sentences from public lectures and quotes are suitable as candidate responses for XiaoIce.
“The unpaired database we have used in XiaoIce consists of sentences collected from public lectures and quotes in news articles and reports. These sentences are considered candidate responses R .”
The paper relies on this without support.
Any individual dialogue skill is unlikely to have a significant impact on CPS.
“Since any individual skill is unlikely to have a significant impact on CPS, we measure the user satisfaction of a skill by monitoring its active users and skill triggering rate (i.e., the number of times a skill is activated by users within a day or a week).”
The paper relies on this without support.
Traditionally, social chatbots are designed for chitchat scenarios where bots are expected to mimic human user conversations but not to interact with the user's environment.
“Traditionally, social chatbots are designed for chitchat scenarios where the bots are expected to mimic human user conversations but not to interact with the user's environment.”
The paper relies on this without support.
Happiness and meaningful conversations often go hand in hand.
“Psychological studies show that happiness and meaningful conversations often go hand in hand.”
The paper relies on this without support.
The long-term success of a social chatbot needs to be measured by its user engagement.
“the long-term success of a social chatbot needs to be measured by its user engagement”
The paper relies on this without support.
The most reliable evaluation is to deploy the chatbot to users and monitor user feedback and engagement over a long period.
“There is no doubt that the most reliable evaluation is to deploy the chatbot to users and monitor the user feedback and engagement, measured by user ratings, NAU, CPS, and so on, over a long period of time.”
The paper relies on this without support.
In open-domain dialog systems, the same input may have many plausible responses that differ in topics or contents significantly.
“Nevertheless, in open-domain dialog systems, the same input may have many plausible responses that differ in topics or contents significantly.”
The paper relies on this without support.
The number of reference responses in the test set is always limited.
“as the number of reference responses is always limited in the test set”

15 of 15

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

Pilot-study dataset is reported as both 4K and 5K sessions
Minor
The description of the second pilot study says its evaluation data consists of 4K dialogue sessions, but the caption of the resulting Table 3 calls it a 5K dialogue dataset.
Image Commenting generator direction is reversed
Minor
The Image Commenting section describes a generator that produces text from images, but its evaluation calls the trained component a text-to-image generator.

2 of 2

A theory of human motivation.
Maslow, A. H. (1943) · Psychological Review · doi:10.1037/h0054346 · Cited by 21,563
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Sequence 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
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278
A THEORY OF HUMAN MOTIVATION
Axford, N. (2017) · Routledge eBooks · doi:10.4324/9781315258324-16 · Cited by 11,329
Introduction to Information Retrieval
Manning, C. D., Raghavan, P., & Schütze, H. (2008) · doi:10.1017/cbo9780511809071 · Cited by 11,288
Untitled work
(2004) · Cited by 9,718
Affective Computing
Picard, R. W. (1997) · MIT Press · doi:10.7551/mitpress/1140.001.0001 · Cited by 7,382
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merriënboer, B., Bahdanau, D., & Bengio, Y. (2014) · SSST@EMNLP · doi:10.3115/v1/w14-4012 · Cited by 7,251
Show and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318

Flagged first, then by citations

Show all 66 references

Research works printed but not linked: 23

Albrecht Joshua, 2007, Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, 880
Asimov I., 1984, “The Bicentennial Man” in I. Asimov, The Bicentennial Man and Other Stories
Banerjee Satanjeev, 2005, Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, 65
Brahnam Sheryl, 2005, Abuse: The Darker Side of Human Computer Interaction, 62
Cuayáhuitl Heriberto, 2018, NeurIPS Workshop on Conversational AI
Dinan Emily, 2018, CoRR
Fang Hao, 2017, Alexa Prize Proceedings
Fung Pascale, 2016, CoRR
Gan Chuang, 2017, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 3137
Ghazvininejad Marjan, 2018, Proceedings of AAAI, 5111
Lin Chin-Yew, 2004, Proceedings of the ACL workshop, 74
Mathews Alexander Patrick, 2016, AAAI, 3574
Misu Teruhisa, 2012, Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 84
Mostafazadeh Nasrin, 2017, Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 462
Papineni Kishore, 2002, Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 311
Sai Ananya, 2019, Proceedings of AAAI 2019, 33, 7281
Serban Iulian Vlad, 2016, AAAI, 16, 3776
Serban Iulian Vlad, 2017, AAAI, 3295
Shum Heung-Yeung, 2018, CoRR
Sutskever Ilya, 2014, NIPS, 3104
Vinyals Oriol, 2015, ICML Deep Learning Workshop
Wu Bowen, 2016, Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, 652
Xing Chen, 2017, AAAI, 17, 3351

Sorted by citations

Items 501–600 of 815

Children in-conflict chatbot system using natural language processing technique
Romilla, P. M., Matuguinas, J., Santiago, A. J., Cortez, D. M. A., Centeno, C. J., Sison, A. A. R. C., & MERCADO, M. A. S. (2023) · World Journal of Advanced Research and Reviews · doi:10.30574/wjarr.2023.18.3.1107 · Cited by 3
Monolingual and Cross-Lingual Knowledge Transfer for Topic Classification
Karpov, D., & Burtsev, M. (2024) · Journal of Mathematical Sciences · doi:10.1007/s10958-024-07421-5 · Cited by 3
XAI Language Tutor - A XAI-based Language Learning Chatbot using Ontology and Transfer Learning Techniques
Shi, N., Zeng, Q. D., & Lee, R. (2020) · International Journal on Natural Language Computing · doi:10.5121/ijnlc.2020.9501 · Cited by 3
The Design and Implementation of Intelligent English Learning Chabot based on Transfer Learning Technology
Shi, N., Zeng, Q., & Lee, R. S. T. (2021) · Advances in Science Technology and Engineering Systems Journal · doi:10.25046/aj060505 · Cited by 3
Affective feature knowledge interaction for empathetic conversation generation
Chen, E., Zhao, H., Li, B., Zha, X., Wang, H., & Wang, S. (2022) · Connection Science · doi:10.1080/09540091.2022.2134301 · Cited by 3
An Adversarially-Learned Turing Test for Dialog Generation ModelsPreprint
Gao, X., Zhang, Y., Galley, M., & Dolan, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.08231 · Cited by 4
AI-Individualism: Understanding New Sociality in the Age of Social Artificial IntelligencePreprint
Brandtzæg, P. B., Skjuve, M. B., & Følstad, A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4804274 · Cited by 3
Using Generative AI Chatbot for enhancing people's digital participation
Pinto, F., & Macadar, M. A. (2024) · International Conference on Theory and Practice of Electronic Governance · doi:10.1145/3680127.3680194 · Cited by 2
Major NLP Applications
Lee, R. (2025) · Natural Language Processing · doi:10.1007/978-981-96-3208-4_9 · Cited by 2
Deconstructing ‘Responsible AI’: An Examination of Legal and Ethical Accountability Through Virtue Jurisprudence
Zhou, S. (2025) · International Journal for the Semiotics of Law - Revue internationale de Sémiotique juridique · doi:10.1007/s11196-025-10388-4 · Cited by 2
Emotional Intelligence: A Human-Centred AI Perspective
Gámez, M. E. (2026) · Springer eBooks · doi:10.1007/978-981-97-8440-0_109-1 · Cited by 2
GAI-HIQ: Developing a health information quality assessment indicator system for generative artificial intelligence
Yi, J., Du, F., Nie, Y., Liang, W., Zhou, X., Chen, J., Li, G., Liu, M., Lv, Y., Zhao, W., et al. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104651 · Cited by 3
Emotional Comfort or Technological Delusion? Unveiling Public Perceptions and Attitudes Toward AI Companions Based on Video Social Medias
Wei, H., Xiang, B., Zheng, X., & Yang, J. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2630076 · Cited by 2
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 3
Generative AI for Mental Well-Being and Insights From High and Low Resource Languages
Sitoula, S., Bhatt, L. P., Pokhrel, A., & Neupane, A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7340-9.ch012 · Cited by 2
Conversational AI and Personal Growth: Insights from a Critical Integrative Review
Sharma, S., Vohra, P., & Vowels, L. M. (2026) · Behavioral Sciences · doi:10.3390/bs16050756 · Cited by 3
Human-like conversational agents as social partners: a scoping review of socioaffective mechanisms, well-being outcomes, risks and governance in the post-Turing era
Li, Q., Geng, H., Hu, X., Pan, D., Liu, H., Li, Y., & Guo, J. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1810097 · Cited by 2
Revisiting Human Identity vis-à-vis AI Evolution
Chen, F., & Tsai, C. (2021) · Caietele Echinox · doi:10.24193/cechinox.2021.40.26 · Cited by 2
Opportunities and threats of using artificial intelligence in the business foresight of Russian companies
Пантелеева, Т. А. (2021) · Market economy problems · doi:10.33051/2500-2325-2021-1-131-148 · Cited by 2
Question 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
MADNet: Maximizing Addressee Deduction Expectation for Multi-Party Conversation Generation
Gu, J.-C., Tan, C.-H., Chu, C., Ling, Z.-H., Tao, C., Liu, Q., & Liu, C. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.476 · Cited by 2
Social Features of Artificial Intelligence Companions for Children
Chang, S. J., Han, S.-H., & Park, K. C. (2023) · Journal of Digital Contents Society · doi:10.9728/dcs.2023.24.12.3199 · Cited by 2
A Framework for Understanding the Weaponisation of the Internet
McLoughlin, I. V. (2023) · IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI) · doi:10.1109/soli60636.2023.10425340 · Cited by 2
Enhancing Chatbot Intelligence Through Narrative Memory Structures
Azam, M., Zafar, L., Rafiq, T., Zafar, S., Rafiq, U., & Adnan, M. (2024) · The Asian Bulletin of Big Data Management · doi:10.62019/abbdm.v4i02.154 · Cited by 2
Building Empathic Chabot using LSTM and NLP
Jeyalakshmi, J., Srinidhi, S. K., & Balaprathap, C. (2024) · International Conference on Innovative Practices in Technology and Management (ICIPTM) · doi:10.1109/iciptm59628.2024.10563763 · Cited by 2
TriKF: Triple-Perspective Knowledge Fusion Network for Empathetic Question Generation
Chen, T., Shen, Y., Chen, X., Zhang, L., & Zhao, S. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3418820 · Cited by 2
Why Conversational AI won’t replace healthcare providers
Gangadharaiah, R., Shivade, C., Bhatia, P., Zhang, Y., & Kass‐Hout, T. (2020) · Cited by 2
Semantic Data Discovery from Social Big Data
Abu-Salih, B., Wongthongtham, P., Zhu, D., Chan, K. Y., & Rudra, A. (2021) · Springer eBooks · doi:10.1007/978-981-33-6652-7_4 · Cited by 2
What Did You Refer to? Evaluating Co-References in Dialogue
Zhang, W., Zhang, Y., Tang, H., Zhao, Z., Zhu, C., & Liu, T. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.450 · Cited by 2
Combining Visual and Social Dialogue for Human-Robot Interaction
Gunson, N., García, D. H., Part, J. L., Yu, Y., Sieińska, W., Dondrup, C., & Lemon, O. (2021) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3462244.3481303 · Cited by 2
Apeak-CG: Automatically predicting emotion based dynamic multi-form knowledge fusion conversation generation
Xu, F., Zhou, S., Wang, X., & Zhang, W. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.06.105 · Cited by 3
Using Extracted Emotion Cause to Improve Content-Relevance for Empathetic Conversation Generation
Zou, M., Pan, R., Zhang, S., & Zhang, X. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-18315-7_8 · Cited by 2
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 2
Intelligent Conversational Chatbots: History, Taxonomy, Classification with PRISMA Model
Gnanaprakasam, J., & Lourdusamy, R. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-71481-8_3 · Cited by 2
Unveiling Trends of Chatbot and Conversational Agents: A Bibliometric Study
Alasali, T., Dakkak, O., & Türker, İ. (2024) · Applied Computer Systems · doi:10.2478/acss-2024-0019 · Cited by 4
Emotional State Estimation by Dialogue History and Sentence Distributed Representation
Matsumoto, K., Sasayama, M., Yoshida, M., & Kita, K. (2019) · IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS) · doi:10.1109/ccis48116.2019.9073750 · Cited by 2
How does your Alexa behave?: Evaluating Voice Applications by Design Guidelines Using an Automatic Voice Crawler.
Han, X., & YEH, T. P. (2020) · Cited by 2
When Creative AI Meets Conversational AI
Wu, X. (2021) · Journal of Natural Language Processing · doi:10.5715/jnlp.28.881 · Cited by 2
Experiences on Creating Personal Study Plans with Chatbots
Koivisto, M. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-21569-8_18 · Cited by 2
Attacks on ML Systems: From Security Analysis to Attack Mitigation
Zou, Q., Zhang, L., Singhal, A., Sun, X., & Liu, P. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-23690-7_7 · Cited by 2
Online Psychological Counseling Chatbot for Seniors
Kim, B., Kim, E., & Rhee, J. (2022) · International Conference on Advances in Artificial Intelligence (ICAAI) · doi:10.1145/3571560.3571583 · Cited by 3
An Intelligent System for Semantic Information Extraction and Knowledge Graph Construction from Multi-Type Data Sources
Zhang, H., Wang, X., Qin, B., & Wang, H. (2022) · IEEE International Conference on e-Business Engineering (ICEBE) · doi:10.1109/icebe55470.2022.00037 · Cited by 2
Foundation Models for Text Generation
Paaß, G., & Giesselbach, S. (2023) · Artificial intelligence: foundations, theory, and algorithms/Artificial intelligence: Foundations, theory, and algorithms · doi:10.1007/978-3-031-23190-2_6 · Cited by 3
Lost in Dialogue: A Review and Categorisation of Current Dialogue System Approaches and Technical Solutions
Kath, H., Lüers, B., Gouvêa, T. S., & Sonntag, D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42608-7_9 · Cited by 3
Conversational Bibliographic Search
Nilles, M. (2024) · Conference on Human Information Interaction and Retrieval · doi:10.1145/3627508.3638337 · Cited by 2
A Multi-talent Healthcare AI Bot Platform
Horn, M., Li, X., Lin, C., & Kafle, S. (2020) · Studies in computational intelligence · doi:10.1007/978-3-030-53352-6_15 · Cited by 2
Investigating person-specific errors in chat-oriented dialogue systems
Mitsuda, K., Higashinaka, R., Li, T., & Yoshida, S. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-short.50 · Cited by 2
Proposal Towards a Personalized Knowledge-powered Self-play Based Ensemble Dialog SystemPreprint
Csáky, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.05016 · Cited by 2
Cue-word Driven Neural Response Generation with a Shrinking VocabularyPreprint
Wang, Q., Liu, Y., Lv, C., Wang, Z., & Fu, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.04927 · Cited by 2
Data-Efficient Methods for Dialogue SystemsPreprint
Shalyminov, I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.02929 · Cited by 3
Graph-Based Transfer Learning for Conversational Agents
Rajan, M. H., Rebello, K. J., Sood, Y., & Wankhade, S. B. (2021) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces51350.2021.9489179 · Cited by 1
Style-sensitive Sentence Embeddings for Evaluating Similarity in Speech Style of Japanese Sentences by Contrastive Learning
Zenimoto, Y., Komata, S., & Utsuro, T. (2023) · doi:10.18653/v1/2023.ijcnlp-srw.5 · Cited by 1
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 2
Keeping the Conversation on Track: Using Large Language Models for Interest Based Topic Management in Child Robot Interactions
Vrins, A. (2025) · ACM International Conference on Interaction Design and Children (IDC) · doi:10.1145/3713043.3731603 · Cited by 1
MindSpeak: An AI-Driven Mobile Application to Enhance Communication Skills for Children with Autism Spectrum Disorder
Ezzat, A. H., Osama, A., Elsherif, F. A., Eldin, M. H., Hesham, K., & Mansour, A. (2025) · International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC) · doi:10.1109/miucc66482.2025.11196837 · Cited by 1
Demystifying the mist: Why do individuals hesitate to accept AI educational services?
Shao, A., Lü, Z., Liu, S. Q., Shi, Y., & Lu, W. (2025) · British Journal of Psychology · doi:10.1111/bjop.70040 · Cited by 1
Leveraging Label Potential for Enhanced Multimodal Emotion Recognition
Shao, X., Yu, Y., & Wang, L. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228349 · Cited by 1
Towards Intelligent Tax Systems: Evaluating NLP Approaches for Pakistan’s Fiscal Needs
Arsal, M., Ashfaq, H., Mahmood, M. A., & Ashfaq, A. (2025) · International Conference on Frontiers of Information Technology (FIT) · doi:10.1109/fit67061.2025.11333725 · Cited by 1
Discussion themes and emotional expressions on Chinese social media regarding AI virtual companions: a topic modeling and sentiment analysis study
Sun, Y., Liu, J., Liu, T., Wei, Z., & Shen, H. (2026) · Frontiers in Psychology · doi:10.3389/fpsyg.2026.1841223 · Cited by 1
Understanding AI-Generated Personal Narratives as Design Material for Socially Engaging Things
Cho, H., Yun, G., Lee, J., & Nam, T.-J. (2022) · [ ] With Design: Reinventing Design Modes · doi:10.1007/978-981-19-4472-7_75 · Cited by 1
Introduction
Gao, J., Xiong, C., Bennett, P. N., & Craswell, N. (2023) · The information retrieval series · doi:10.1007/978-3-031-23080-6_1 · Cited by 1
Self-citation
Research on Intelligent Dialogue Systems
Hu, S. (2023) · Theoretical and Natural Science · doi:10.54254/2753-8818/2/20220175 · Cited by 1
Predicting the Subjective Responses’ Emotion in Dialogues with Multi-Task Learning
Hayat, H., Ventura, C., & Lapedriza, À. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-36616-1_55 · Cited by 1
Multi-modal sentiment analysis based on expression and text
Kao, W., Yang, H., Liu, C., & Bai, J. (2023) · International Conference on Advanced Algorithms and Neural Networks (AANN) · doi:10.1117/12.3004687 · Cited by 1
TAKE: Tracing Associative Empathy Keywords for Generating Empathetic Responses Based on Graph Attention
Liu, K., Song, M., Xu, W., Li, K. E., Peng, M., & Tian, G. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0573-6_3 · Cited by 1
Effectiveness of Artificial Intelligence in Economics: A Comparative Analysis of Three Free AI Chatbots
Siddiquee, M., & -, M. J. (2025) · International Journal For Multidisciplinary Research · doi:10.36948/ijfmr.2025.v07i02.40428 · Cited by 1
Advancements and Challenges in Conversational AI: Navigating the Frontiers of Innovation and Complexity
Sanjeev, A., & Sharma, R. (2025) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-83549-852-120251006 · Cited by 1
Technological Evolution and Research Trends of Intelligent Question-Answering Systems in Healthcare
Lei, B., & Yin, P. (2025) · Healthcare · doi:10.3390/healthcare13182269 · Cited by 1
Navigating Copyright Protection for AI Works: Insights from China, Japan, and Recommendations for Vietnam
Châm, N. T. P. (2025) · Architecture Image Studies · doi:10.62754/ais.v6i3.289 · Cited by 1
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
International Al Safety Report: First Key Update Capabilities and Risk Implications
Bengio, Y., Bucknall, B., Clare, S., Prunkl, C., Andriushchenko, M., Fox, P., Hu, T., Jones, C., Manning, S., Maslej, N., et al. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i6.16253 · Cited by 1
AI-Based Chatbots for Mental Health: Comparative Study
Ech-Cheikh, S., Kharmoum, N., & Ziti, S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-01970-7_6 · Cited by 1
Investigating the Influence of Personalization and Context Awareness on User Experience in AI-Driven Customer Support Chatbots
Jain, R., & Rani, S. (2026) · Shodh Manjusha An International Multidisciplinary Journal · doi:10.70388/sm250192 · Cited by 1
Evaluating chatbots’ adherence to the integrated model of advice giving: presence and sequential structuring of supportive acts in human-AI interactions
Hwang, L. J., Li, H., & Feng, B. (2026) · Behaviour and Information Technology · doi:10.1080/0144929x.2026.2633768 · Cited by 1
Will customers buy financial products impulsively? AI-powered chatbots’ recommendations
Cheng, Y.-M. (2026) · Journal of Asia Business Studies · doi:10.1108/jabs-06-2025-0340 · Cited by 1
From Jugaad to Generative AI: A Framework for Culturally Responsive Human-Centered AI
Rathore, N. S., & Thakkar, S. (2025) · International Association of Societies of Design Research Congress (IASDR) · doi:10.21606/iasdr.2025.537 · Cited by 1
Virtual Love, Real Loss
Wu, Y. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-6623-4.ch007 · Cited by 1
Tapping out, talking in: what drives users to ditch menu-based navigation and switch to voice and text AI-based chatbots in mobile banking?
Dawood, H., Liew, C. Y., & Rajan, M. E. S. (2026) · International Journal of Intelligent Computing and Cybernetics · doi:10.1108/ijicc-11-2025-0771 · Cited by 1
Digital Darwinism: steering the evolution of artificial life in socio-technical systems
Ulrich, K. T. (2026) · AI and Ethics · doi:10.1007/s43681-026-01057-8 · Cited by 1
Harnessing Artificial Intelligence to Facilitate Difficult Conversations
Maheshka, C., Folk, D. P., & Dunn, E. (2026) · Social Psychological and Personality Science · doi:10.1177/19485506261444068 · Cited by 1
Bridging the silos in affective AI: a critical perspective from data to society
Inoshita, K. (2026) · AI & Society · doi:10.1007/s00146-026-03324-y · Cited by 1
Reimagining work in the age of AI: a multilevel review of individual, organizational, and societal dynamics
Liu, P., Zhu, P., Yuan, Y. E., Zhao, F., & Liu, B. (2026) · Current Psychology · doi:10.1007/s12144-026-09403-z · Cited by 1
Empathy through the Lens of Conversational Agents: A Systematic Review
Khadka, S., & Desai, S. (2026) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3816046.3816220 · Cited by 1
I hear you: Enhancing middle school mathematics engagement and learning outcomes through teachable agent voice design
Li, H., Xing, W., Li, C., & Lyu, B. (2026) · Computers & Education · doi:10.1016/j.compedu.2026.105725 · Cited by 1
Platform-Facilitated Grooming and AI Chatbots: Rethinking Criminal Liability and Regulation
Chawki, M. (2026) · Laws · doi:10.3390/laws15040093 · Cited by 1
Rechat: Ferramenta para Estudo do Comportamento de Usuários em Sistemas de Bate-papo do Estilo WhatsApp
Ribas, L. R., Gomes-Jr, L., & Silva, T. H. (2020) · Brazilian Symposium on Multimedia and the Web · doi:10.5753/webmedia_estendido.2020.13067 · Cited by 1
How to Evaluate a Good Conversation? An Evaluation Framework for Chat Experience in Smart Home
Chen, X., Ma, L., Jia, M., Han, Y., Mi, J., & Xu, M. Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-78462-1_27 · 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
Self-citation
Dialogue Response Generation for Text-Based Dialogue Systems with Emotion Regulation
Katayama, S., Yonezawa, T., & Kawaguchi, N. (2022) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.34.3_568 · Cited by 1
An Automatic Evaluation Method for Open-domain Dialogue Based on BLEURT
Wu, S.-H., & Lee, J.-J. (2022) · IEEE International Conference on Information Reuse and Integration (IRI) · doi:10.1109/iri54793.2022.00030 · Cited by 1
The Gendered Nature of Chatbots
Ashcroft, A., & Ashcroft, A. (2023) · Advances in web technologies and engineering book series · doi:10.4018/978-1-6684-6234-8.ch003 · Cited by 1
Proactivity in Conversational Assistants: The mPLiCA Model Based on a Systematic Literature Review
Johnson, E., Villa, L., Mondéjar, T., & Hervás, R. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-48306-6_28 · Cited by 1
Center-retained fine-tuning for conversational question ranking through unsupervised center identification
Liu, Z., Chen, Z., Ren, Z., Gao, S., Ma, J., & Ren, P. (2023) · Information Processing & Management · doi:10.1016/j.ipm.2023.103578 · Cited by 1
Chatbot using Artificial Intelligence Markup Language
(2024) · International Research Journal of Modernization in Engineering Technology and Science · doi:10.56726/irjmets48132 · Cited by 1
Empathy-Driven Chatbots for the Arabic Language: A Transformer Based Approach
Rabii, I., Boussakssou, M., & Erritali, M. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-53082-1_5 · Cited by 1
Toward an end-to-end implicit addressee modeling for dialogue disentanglement
Gao, J., Li, Z., Xiang, S., Wang, Z., Liu, T., & Fu, Y. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18428-0 · Cited by 1
Self-citation
Learning WHO Saying WHAT to WHOM in Multi-Party Conversations
Gu, J.-C., Zhang, Z., & Ling, Z.-H. (2023) · doi:10.18653/v1/2023.ijcnlp-tutorials.5 · Cited by 2
Enhancing Emotion Recognition in Conversation with Dialogue Discourse Structure and Commonsense Knowledge
Hao, J., Kong, F., & Kang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5672-8_22 · Cited by 1
Constructing an English Language Chatbot Using Reinforcement Learning Algorithms
Xu, B. (2024) · International Conference on Artificial Intelligence and Autonomous Robot Systems (AIARS) · doi:10.1109/aiars63200.2024.00070 · Cited by 1
The Application of Artificial Intelligence in the Administration of Criminal Law and the Procedures Involved in Criminal Cases
Rahman, A. T. A. S., & Kaur, A. (2024) · IEEE International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET) · doi:10.1109/acroset62108.2024.10743336 · Cited by 1

Authors: Zhou, L., Gao, J., Li, D., & Shum, H.-Y.
Affiliations: Microsoft (United States) (US)
ORCID: Gao, Jianfeng
Li, Di
Shum, Heung-Yeung
Venue: Computational Linguistics
Publisher: MIT Press
Published: 2020-03
Volume: 46
Issue: 1
Pages: 53-93
ISSN: 0891-2017 (ISSN-L)
1530-9312
DOI: 10.1162/coli_a_00368
OpenAlex: W2906579211
Semantic Scholar: 66b7d31527f980bb2eecc23629f08ba6037facc4
Cited by: 777
References: 66
Citations by year: 2026: 97 · 2025: 109 · 2024: 106 · 2023: 113 · 2022: 120 · 2021: 112 · 2020: 94
FWCI: 43.11
Type: journal article
Language: en
Open access: diamond
doi.org
Licence: cc-by-nc-nd
Locations: Computational Linguistics (publishedVersion, cc-by-nc-nd)
arXiv (Cornell University) (submittedVersion)
Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
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, Markov decision process, dialogue management, user engagement, emotion recognition, user intent understanding

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.

A language model drew the claims from the paper on 2026-10-08, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-08 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

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

The Design and Implementation of XiaoIce, an Empathetic Social Chatbot

Abstract

Overview

AI snapshot

TL;DR

Key findings

Methods

Limitations

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Self-check

Citations

Cites

Cited by

Related

Metadata

Record

About these checks