Twitter Trend Extraction: A Graph-based Approach for Tweet and Hashtag Ranking, Utilizing No-Hashtag Tweets

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 6213–6219 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 6213 Twitter Trend Extraction: A Graph-based Approach for Tweet and Hashtag Ranking, Utilizing No-Hashtag Tweets Zahra Majdabadi, Behnam Sabeti, Preni Golazizian, Seyed Arad Ashrafi Asli Omid Momenzadeh and Reza Fahmi Miras Technologies International Number 92, Movahed Danesh St., Tehran, Iran {zahra, behnam, preni, arad, omid, reza}@miras-tech.com Abstract Twitter has become a major platform for users to express their opinions on any topic and engage in debates. User debates and interactions usually lead to massive content regarding a specific topic which is called a Trend. Twitter trend extraction aims at finding these relevant groups of content that are generated in a short period. The most straightforward approach for this problem is using Hashtags, however, tweets without hashtags are not considered this way. In order to overcome this issue and extract trends using all tweets, we propose a graph-based approach where graph nodes represent tweets as well as words and hashtags. More specifically, we propose a modified version of RankClus algorithm to extract trends from the constructed tweets graph. The proposed approach is also capable of ranking tweets, words and hashtags in each trend with respect to their importance and relevance to the topic. The proposed algorithm is used to extract trends from several twitter datasets, where it produced consistent and coherent results. Keywords: Twitter Trend Extraction, Tweet Clustering, Graph Representation, EM Algorithm 1. Introduction Today several platforms are offering users the opportunity to express their opinions on emerging topics related to on- going events in their lives as well as national and interna- tional matters. Among these platforms, Twitter has become a major player, in which users tend to express their opin- ions on any topics and engage in debates posting millions of tweets every day. User debates and interactions usually lead to massive content regarding a specific topic which is called a Trend. Twitter trends are specifically important due to their influence on public opinion and their ability to affect politicians, governments, organizations, compa- nies and almost any other entities. Twitter trend extraction, as the name suggests, is aimed at detecting ongoing trends among millions of tweets that are posted rapidly. Being able to automatically detect and extract these trends is ap- pealing to anyone interested in analyzing hot topics and on- going online debates. There are two main approaches for automatic trend ex- traction: embedding based and graph-based. Embedding based approaches try to find a vector representation of each tweet and detect groups of similar tweets that could indi- cate trends. On the other hand, in graph-based methods, the goal is to represent tweets as a graph and employ graph clustering algorithms in order to extract similar sub-graphs as trends. Many twitter users tend to use hashtags, which indicate the main topic of their tweets. Hashtags can also be very useful to find similar tweets and follow debates related to specific topics. …

Content truncated to 500 words