Preliminary Conference Agenda

Overview and details of the sessions of this conference. Please select a date or room to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).

This agenda is preliminary and subject to change.

Session Overview
Preliminary Papers 10: Social Media
Wednesday, 28/Mar/2018:
11:00am - 12:30pm

Session Chair: Laura Sbaffi, University of Sheffield
Location: Lecture Theatre 4 (Diamond)
The Diamond

Show help for 'Increase or decrease the abstract text size'

Social Content Management: A Study on Issues and Challenges



Organisations are facing challenges in managing the diverse social content resulting from the active interactions between them and their customers on social media platforms. The increasing opportunities from social content have led to the concept of social content management (SCM). However, research in SCM is yet to receive more attention, especially in the context of its issues and challenges. Therefore, this paper has evaluated the issues and challenges in SCM research from the academic and practical viewpoint. Since the number of academic research in SCM is limited, this paper offers a point of departure for future studies in the SCM field. In the context of practical contribution, this study aimed to offer better understanding of the issues and challenges in managing social content.

Towards Understanding Cross-cultural Crowd Sentiment using Social Media

Yuanyuan Wang1, Panote Siriaraya2, Muhammad Syafiq Mohd Pozi3, Yukiko Kawai2, Adam Jatowt4

1Yamaguchi University, Japan; 2Kyoto Sangyo University, Japan; 3Universiti Tenaga Nasional, Malaysia; 4Kyoto University, Japan

Social media such as Twitter has been frequently used for expressing personal opinions and sentiments at different places. In this paper, we propose a novel crowd sentiment analysis for fostering cross-cultural studies. In particular, we aim to find similar meanings but different sentiments between tweets collected over geographical areas. For this, we detect sentiments and topics of each tweet by applying neural network based approaches, and we assign sentiments to each topic based on the sentiments of the corresponding tweets. This permits finding cross-cultural patterns by computing topic and sentiment correspondence. The proposed methods enable to analyze tweets from diverse geographical areas sentimentally in order to explore cross-cultural differences.

Sentiments in Wikipedia Articles for Deletion Discussions

Lu Xiao, Niraj Sitaula

Syracuse University, United States of America

Wikipedia provides a discussion forum, namely, Article for Deletion forum, for people to deliberate about whether or not an article should be deleted from the site. In this paper, we present interesting correlation between out-comes of the discussion and number of sentiments in the comments with different intensity. We performed sentiment analysis on 37,761 AfD discussions with 156,415 top-level comments and explored relationship between outcomes of the discussion and sentiments in the comments. Our preliminary work suggests: discussion that have keep or other outcomes have more than expected positive sentiment, whereas discussions that have delete out-comes have more than expected negative and neutral sentiment. This result shows that there tends to be positive sentiment in the comment when Wikipedia users suggest not to delete the article. This observation of differences in sentiments also encourages to further study influence of sentiments in decision making or outcome of the discussions. Our future analysis will include threaded comments, and examine the relationship between a discussion’s sentiment and its other properties such as topic of the article and the characteristics of the participating users.

A Comparison of the Historical Entries in Wikipedia and Baidu Baike

Wenyi Shang

Peking University, China, People's Republic of

Online encyclopedias are exerting more and more influence on people’s everyday information seeking. However, their reliability is questioned by many experts. This research chose two representative online encyclopedias, Wikipedia (English) and Baidu Baike, to compare their performance on historical entries.

Six entries were chosen as examples, representing three categories, historic place, historical event, and historical figure. In order to compare, this research divided the articles in both encyclopedias into many pieces of quantifiable information. By judging the accuracy of each piece, this research calculated the precision rate of each encyclopedia. Moreover, five graduates from the History Department are invited to give grades to the information to judge the width and depth, and the results were verified by research on authoritative works.

The results show that: (1) Wikipedia is superior in accuracy, width and depth in most entries. (2) Baidu Baike is a little better in the entries on Chinese history. The operating mechanism of the two encyclopedias is the most important reason for the results. Besides, the passive actuality of World history research in China is also responsible.

The results imply that in the field of history, well-established online encyclopedias like Wikipedia can be reliable for common users while Baidu Baike still needs improvement. Online encyclopedias may improve their levels of authority by developing operating mechanisms.

Contact and Legal Notice · Contact Address:
Conference: iConference 2018
Conference Software - ConfTool Pro 2.6.122+TC
© 2001 - 2018 by Dr. H. Weinreich, Hamburg, Germany