Abstract—Social media has gained a lot of popularity and become the main source of information. Recently, immediate popular news or stories, known as trending topics have found social networks, such as Twitter, an attractive platform for its spread. Detection of trending topics from social media is a commonly tackled issue in the data mining community as it helps in different applications, such as news agencies discovering breaking news in real-time or marketing departments detecting viral memes. In this paper, we explore trending topic detection from social media, specifically twitter, using the ratio frequency of the hashtags. The proposed system is bilingual as it detects trending topics in both Arabic and English tweets. We classify the trending topics into four classes to help identify and rank the topics of interests to the community. These trending topics are visualized on a spatio-temporal map that allows users discover the spatial distribution of these topics as well as their time intervals. We have experimented with different textual features to detect trending topics and described the results and tradeoffs of using these features.
 

Index Terms—trend topics, hashtags, spatio-temporal visualization, data mining, Twitter

Cite: Balsam Alkouz and Zaher Al Aghbari, "Detection and Visualization of Bilingual Trending Topics," Journal of Advances in Information Technology, Vol. 11, No. 2, pp. 71-77, May 2020. doi: 10.12720/jait.11.2.71-77

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.