Automatic opinion leader recognition in group discussions

Yu Chang Ho, Hao Min Liu, Hui Hsin Hsu, Chun Han Lin, Yao Hua Ho, Ling Jyh Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In this paper, we propose an efficient approach to identify the opinion leader from group discussion. This approach is able to recognize the opinion leader without analyzing semantic and syntactic features, which may cost a lot more computing effort. We firstly propose algorithms to evaluate the degree of participation and the emotion expression from the speaking of each member during group discussion. Moreover, by conducting lab-scale experiment, a well-trained model, which is tested on single dataset as well as on cross dataset, is obtained to recognize the opinion leader. Finally, we conduct a field experiment to evaluate the proposed system in a real world setting. The results show that the accuracy of opinion leader identification could achieve to 94.68% on Berlin dataset, 76% on Youtube data and 73.33% on live group discussion. Thus, with this simple and efficient system, opinion leader can be successfully identified in various conditions.

Original languageEnglish
Title of host publicationTAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages138-145
Number of pages8
ISBN (Electronic)9781509057320
DOIs
Publication statusPublished - 2017 Mar 16
Event2016 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2016 - Hsinchu, Taiwan
Duration: 2016 Nov 252016 Nov 27

Publication series

NameTAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings

Other

Other2016 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2016
CountryTaiwan
CityHsinchu
Period16/11/2516/11/27

Fingerprint

Syntactics
Field Experiment
Evaluate
Experiments
Semantics
Costs
Computing
Experiment
Model
Emotion
Participation
Syntax

Keywords

  • Word-of-mouth communication
  • emotion recognition
  • group discussion
  • influence
  • opinion leader

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Control and Optimization
  • Information Systems

Cite this

Ho, Y. C., Liu, H. M., Hsu, H. H., Lin, C. H., Ho, Y. H., & Chen, L. J. (2017). Automatic opinion leader recognition in group discussions. In TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings (pp. 138-145). [7880177] (TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TAAI.2016.7880177

Automatic opinion leader recognition in group discussions. / Ho, Yu Chang; Liu, Hao Min; Hsu, Hui Hsin; Lin, Chun Han; Ho, Yao Hua; Chen, Ling Jyh.

TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 138-145 7880177 (TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ho, YC, Liu, HM, Hsu, HH, Lin, CH, Ho, YH & Chen, LJ 2017, Automatic opinion leader recognition in group discussions. in TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings., 7880177, TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 138-145, 2016 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2016, Hsinchu, Taiwan, 16/11/25. https://doi.org/10.1109/TAAI.2016.7880177
Ho YC, Liu HM, Hsu HH, Lin CH, Ho YH, Chen LJ. Automatic opinion leader recognition in group discussions. In TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 138-145. 7880177. (TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings). https://doi.org/10.1109/TAAI.2016.7880177
Ho, Yu Chang ; Liu, Hao Min ; Hsu, Hui Hsin ; Lin, Chun Han ; Ho, Yao Hua ; Chen, Ling Jyh. / Automatic opinion leader recognition in group discussions. TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 138-145 (TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings).
@inproceedings{28a394dd7622432bb37cfe5f707da5d6,
title = "Automatic opinion leader recognition in group discussions",
abstract = "In this paper, we propose an efficient approach to identify the opinion leader from group discussion. This approach is able to recognize the opinion leader without analyzing semantic and syntactic features, which may cost a lot more computing effort. We firstly propose algorithms to evaluate the degree of participation and the emotion expression from the speaking of each member during group discussion. Moreover, by conducting lab-scale experiment, a well-trained model, which is tested on single dataset as well as on cross dataset, is obtained to recognize the opinion leader. Finally, we conduct a field experiment to evaluate the proposed system in a real world setting. The results show that the accuracy of opinion leader identification could achieve to 94.68{\%} on Berlin dataset, 76{\%} on Youtube data and 73.33{\%} on live group discussion. Thus, with this simple and efficient system, opinion leader can be successfully identified in various conditions.",
keywords = "Word-of-mouth communication, emotion recognition, group discussion, influence, opinion leader",
author = "Ho, {Yu Chang} and Liu, {Hao Min} and Hsu, {Hui Hsin} and Lin, {Chun Han} and Ho, {Yao Hua} and Chen, {Ling Jyh}",
year = "2017",
month = "3",
day = "16",
doi = "10.1109/TAAI.2016.7880177",
language = "English",
series = "TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "138--145",
booktitle = "TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings",

}

TY - GEN

T1 - Automatic opinion leader recognition in group discussions

AU - Ho, Yu Chang

AU - Liu, Hao Min

AU - Hsu, Hui Hsin

AU - Lin, Chun Han

AU - Ho, Yao Hua

AU - Chen, Ling Jyh

PY - 2017/3/16

Y1 - 2017/3/16

N2 - In this paper, we propose an efficient approach to identify the opinion leader from group discussion. This approach is able to recognize the opinion leader without analyzing semantic and syntactic features, which may cost a lot more computing effort. We firstly propose algorithms to evaluate the degree of participation and the emotion expression from the speaking of each member during group discussion. Moreover, by conducting lab-scale experiment, a well-trained model, which is tested on single dataset as well as on cross dataset, is obtained to recognize the opinion leader. Finally, we conduct a field experiment to evaluate the proposed system in a real world setting. The results show that the accuracy of opinion leader identification could achieve to 94.68% on Berlin dataset, 76% on Youtube data and 73.33% on live group discussion. Thus, with this simple and efficient system, opinion leader can be successfully identified in various conditions.

AB - In this paper, we propose an efficient approach to identify the opinion leader from group discussion. This approach is able to recognize the opinion leader without analyzing semantic and syntactic features, which may cost a lot more computing effort. We firstly propose algorithms to evaluate the degree of participation and the emotion expression from the speaking of each member during group discussion. Moreover, by conducting lab-scale experiment, a well-trained model, which is tested on single dataset as well as on cross dataset, is obtained to recognize the opinion leader. Finally, we conduct a field experiment to evaluate the proposed system in a real world setting. The results show that the accuracy of opinion leader identification could achieve to 94.68% on Berlin dataset, 76% on Youtube data and 73.33% on live group discussion. Thus, with this simple and efficient system, opinion leader can be successfully identified in various conditions.

KW - Word-of-mouth communication

KW - emotion recognition

KW - group discussion

KW - influence

KW - opinion leader

UR - http://www.scopus.com/inward/record.url?scp=85017577314&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017577314&partnerID=8YFLogxK

U2 - 10.1109/TAAI.2016.7880177

DO - 10.1109/TAAI.2016.7880177

M3 - Conference contribution

AN - SCOPUS:85017577314

T3 - TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings

SP - 138

EP - 145

BT - TAAI 2016 - 2016 Conference on Technologies and Applications of Artificial Intelligence, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -