Analyzing and Characterizing User Intent in Information-seeking Conversations

被引:65
|
作者
Qu, Chen [1 ]
Yang, Liu [1 ]
Croft, W. Bruce [1 ]
Trippas, Johanne R. [2 ]
Zhang, Yongfeng [3 ]
Qiu, Minghui [4 ]
机构
[1] Univ Massachusetts Amherst, Amherst, MA 01003 USA
[2] RMIT Univ, Melbourne, Vic, Australia
[3] Rutgers State Univ, New Brunswick, NJ USA
[4] Alibaba Grp, Hangzhou, Zhejiang, Peoples R China
来源
基金
美国国家科学基金会;
关键词
Information-seeking; Conversational Search; User Intent;
D O I
10.1145/3209978.3210124
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Understanding and characterizing how people interact in information-seeking conversations is crucial in developing conversational search systems. In this paper, we introduce a new dataset designed for this purpose and use it to analyze information-seeking conversations by user intent distribution, co-occurrence, and flow patterns. The MSDialog dataset is a labeled dialog dataset of question answering (QA) interactions between information seekers and providers from an online forum on Microsoft products. The dataset contains more than 2,000 multi-turn QA dialogs with 10,000 utterances that are annotated with user intent on the utterance level. Annotations were done using crowdsourcing. With MSDialog, we find some highly recurring patterns in user intent during an information-seeking process. They could be useful for designing conversational search systems. We will make our dataset freely available to encourage exploration of information-seeking conversation models.
引用
收藏
页码:989 / 992
页数:4
相关论文
共 50 条
  • [1] User Intent Prediction in Information-seeking Conversations
    Qu, Chen
    Yang, Liu
    Croft, W. Bruce
    Zhang, Yongfeng
    Trippas, Johanne R.
    Qiu, Minghui
    PROCEEDINGS OF THE 2019 CONFERENCE ON HUMAN INFORMATION INTERACTION AND RETRIEVAL (CHIIR'19), 2019, : 25 - 33
  • [2] Analyzing clarification in asynchronous information-seeking conversations
    Tavakoli, Leila
    Zamani, Hamed
    Scholer, Falk
    Croft, William Bruce
    Sanderson, Mark
    JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY, 2022, 73 (03) : 449 - 471
  • [3] Analysis of Information-Seeking Conversations with Process Mining
    Holstrup, Alexander
    Starklit, Lasse
    Burattin, Andrea
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [4] User involvement and user satisfaction with information-seeking activity
    Santosa, PI
    Wei, KK
    Chan, HC
    EUROPEAN JOURNAL OF INFORMATION SYSTEMS, 2005, 14 (04) : 361 - 370
  • [5] Learning to Expand: Reinforced Response Expansion for Information-seeking Conversations
    Pan, Haojie
    Chen, Cen
    Wang, Chengyu
    Qiu, Minghui
    Yang, Liu
    Ji, Feng
    Huang, Jun
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 4055 - 4064
  • [6] InSCIt: Information-Seeking Conversations with Mixed-Initiative Interactions
    Wu, Zeqiu
    Parish, Ryu
    Cheng, Hao
    Min, Sewon
    Ammanabrolu, Prithviraj
    Ostendorf, Mari
    Hajishirzi, Hannaneh
    TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 2023, 11 : 453 - 468
  • [7] Information-Seeking Behaviors of Education Literature User Populations
    Wright, Carol
    TEACHERS COLLEGE RECORD, 2010, 112 (10): : 2537 - 2564
  • [8] Conversations with chemists: Information-seeking behavior of chemistry faculty in the electronic age
    Flaxbart, D
    SCIENCE & TECHNOLOGY LIBRARIES, 2001, 21 (3-4) : 5 - 26
  • [9] AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models
    Li, Siheng
    Yang, Cheng
    Yin, Yichun
    Zhu, Xinyu
    Cheng, Zesen
    Shang, Lifeng
    Jiang, Xin
    Liu, Qun
    Yang, Yujiu
    61ST CONFERENCE OF THE THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL 2023, VOL 2, 2023, : 1751 - 1762
  • [10] Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
    Aliannejadi, Mohammad
    Zamani, Hamed
    Crestani, Fabio
    Croft, W. Bruce
    PROCEEDINGS OF THE 42ND INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '19), 2019, : 475 - 484