Time-Sensitive Hashtag Frequency-Inverse Hashtag Ubiquity (THF-IHU) Algorithm for Hashtag Recommendation in Twitter
Shang-Ke Gu, Rachsuda Setthawong · 2022 19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) · 2022
Hashtag recommendation is a challenging task for social networks, but there are not many works focusing on time-sensitive recommendations. This paper proposes an enhanced algorithm namely Time-Sensitive Hashtag Frequency-Inverse Hashtag Ubiquity (THF-IHU) for hashtag recommendation system in Twitter, which is based on Hashtag Frequency-Inverse Hashtag Ubiquity (HF-IHU) algorithm. The proposed algorithm integrates two main features: a time feature for altering weight, and the feature taken from the BM25 ranking function which adjusts weight based on documents’ length. The experimental result on a Twitter dataset shows that the enhanced algorithm outperforms the traditional algorithm by over 35 percent in terms of recall.