Automatic meeting summarization and topic detection system

Publication Date02 July 2018
Date02 July 2018
AuthorTai-Chia Huang,Chia-Hsuan Hsieh,Hei-Chia Wang
SubjectLibrary & information science,Librarianship/library management,Library technology,Information behaviour & retrieval,Metadata,Information & knowledge management,Information & communications technology,Internet
Automatic meeting
summarization and topic
detection system
Tai-Chia Huang and Chia-Hsuan Hsieh
Department of Industrial and Information Management,
National Cheng Kung University, Tainan, Taiwan, and
Hei-Chia Wang
Institute of Information Management,
National Cheng Kung University, Tainan, Taiwan
Purpose Producing meeting documents requires an instantaneous recorder during meetings, which costs
extra human resources and takes time to amend the file. However, a high-quality meeting document can
enable users to recall the meeting content efficiently. The paper aims to discuss these issues.
Design/methodology/approach An application based on this framework is developed to help the users find
topics and obtain summarizations of meeting contents without extra effort. This app uses the Bluemix speech
recognizer to obtain speech transcripts. It then combines latent Dirichlet allocation and a TextTiling algorithm with
the speech script of meetings to detect boundaries between different topics and evaluate the topics in each segment.
TextTeaser, an open API based on a feature-based approach, is then used to summarize the speech transcripts.
Findings The results indicate that the summaries generated by the machine are 85 percent similar to the
records written by humankind.
Originality/value To reduce the human effort in generating meeting reports, this paper presents a
framework to record and analyze meeting contents automatically by voice recognition, topic detection,
and extractive summarization.
Keywords Text analysis, Extractive summarization, Intelligent system, LDA model,
TextTiling, Topic detection
Paper type Research paper
1. Introduction
Meetings are an important activity in organizations. During a meeting, massive amounts of
data must be recorded in text format. The quality of records affects the organization process
because the decisions made in meetings usually frame the rules for future work. To obtain
quality records, human effort is required when annotating transcripts and summaries.
Therefore, many organizations ask a reliable secretary to perform this job. Recently,
research has suggested that artificial intelligence may take over certain record-keeping jobs
(Dungan and Chandler, 1985, Hsiao et al., 2017). In this paper, a framework is presented to
achieve this goal. Although some researchers have examined the role of artificial intelligent
agents in analyzing discussion, their works have focused primarily on broadcast news
transcripts (Hori et al., 2003). However, meetings differ from broadcast news in numerous
ways. For example, different opinions and topics are discussed in a meeting. With few
textual and structural features, detecting topics and providing summarization is a
significant challenge. In addition, online meetings occur frequently in the internet era.
Noting these factors, this paper proposes an approach for detecting discussion topics and
summarizing meeting transcripts by integrating several algorithms. This framework
includes three parts: speech recognition, topic detection, and extractive summarization. Data Technologies and
Vol. 52 No. 3, 2018
pp. 351-365
© Emerald PublishingLimited
DOI 10.1108/DTA-09-2017-0062
Received 13 September 2017
Revised 6 February 2018
Accepted 10 March 2018
The current issue and full text archive of this journal is available on Emerald Insight at:
The research was based on the work supported by the Taiwan Ministry of Science and Technology
under Grant No. MOST 103-2410-H-006-055-MY3.

To continue reading

Request your trial

VLEX uses login cookies to provide you with a better browsing experience. If you click on 'Accept' or continue browsing this site we consider that you accept our cookie policy. ACCEPT