Tag Recommendation for Online Q&A Communities based on BERT Pre-Training Technique

TL;DR

This paper introduces TagBERT, a novel tag recommendation method for online Q&A communities using BERT pre-training, which improves accuracy and stability over existing deep learning approaches.

Contribution

The study applies BERT pre-training to tag recommendation in online communities for the first time, demonstrating superior accuracy and stability.

Findings

TagBERT outperforms baseline methods in accuracy.

The model maintains high performance as the number of recommended tags increases.

Improved stability addresses previous issues of performance degradation.

Abstract

Online Q&A and open source communities use tags and keywords to index, categorize, and search for specific content. The most obvious advantage of tag recommendation is the correct classification of information. In this study, we used the BERT pre-training technique in tag recommendation task for online Q&A and open-source communities for the first time. Our evaluation on freecode datasets show that the proposed method, called TagBERT, is more accurate compared to deep learning and other baseline methods. Moreover, our model achieved a high stability by solving the problem of previous researches, where increasing the number of tag recommendations significantly reduced model performance.