Measuring User Influence Based on Multiple Metrics on YouTube

Abstract

User influence in online social networks has been measured by different metrics and algorithms, and these methods roughly fall into two main genres: attribute-based approaches and graph-based approaches. However, most attribute-based approaches only consider single metric, such as total view counts or retweet counts. And graph-based approaches cannot apply to the platforms where it is difficult to obtain graphs of some metrics. In this paper, we propose a triangular fuzzy number-based method to measure user influence, which covers multiple metrics and is graph free. By taking You Tube as an example, based on triangular fuzzy number, we synthesize view, comment and like counts to measure user influence. We first compute the triangular fuzzy number of each metric to represent user influence, and then use the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method to synthesize multiple triangular fuzzy numbers and rank users. The experiments based on You Tube data show that, when only considering view counts, our results are in good agreement with other popular measures such as h-index. However, beyond view counts, our method provides a comprehensive measure which can cover multiple metrics.