Identifying topic-based opinion leaders in social networks by content and user information

Abstract

Social media is like a revolution since it has changed many things in people’s lifestyles by bringing new trends in communication, shopping, working…etc. Inspired by the importance of social media, we propose Opinion Leader Detection (OLED) system in this paper. OLED has two main parts. In the first part, the tweets were labeled with their categories by semantic kernels for topic-based analysis. We run these semantic kernels and their variants with SVM in our experiment environment. After LDA and these semantic classifiers, obtain category information for each tweet in the dataset. OLED’s second part attempts to detect whether the users are opinion leaders in their category. Then, the leadership scores are calculated with the formula generated and opinion leaders are determined in each category. The purpose of OLED is to find the opinion leaders for each category. In other words, OLED aims to detect opinion leaders for different topics such as Economy, Culture-Art, Politics, Sports and Technology. We performed our experiments on a real data collection gathered from Twitter that includes 17,234,924 tweets and 38,727 users. The language of the dataset is Turkish. Users with highest scores are stated as opinion leaders. In order to evaluate OLED’s performance, we also run PageRank algorithm on the same dataset. We also compare our study to one of the existing studies in the literature. The experimental results show that our framework OLED generates remarkable performance in compare to PageRank algorithm nearly in all topics and all selected top number of opinion leaders.