A Comparative Analysis of Transformer Models in Social Bot Detection
It addresses the problem of bot manipulation in online discussions for social media platforms and researchers, but is incremental as it compares existing transformer types without introducing new methods.
This paper compared encoder and decoder transformer models for detecting social media bots, finding that encoder-based classifiers had higher accuracy and robustness, while decoder-based models showed greater adaptability and potential for generalization.
Social media has become a key medium of communication in today's society. This realisation has led to many parties employing artificial users (or bots) to mislead others into believing untruths or acting in a beneficial manner to such parties. Sophisticated text generation tools, such as large language models, have further exacerbated this issue. This paper aims to compare the effectiveness of bot detection models based on encoder and decoder transformers. Pipelines are developed to evaluate the performance of these classifiers, revealing that encoder-based classifiers demonstrate greater accuracy and robustness. However, decoder-based models showed greater adaptability through task-specific alignment, suggesting more potential for generalisation across different use cases in addition to superior observa. These findings contribute to the ongoing effort to prevent digital environments being manipulated while protecting the integrity of online discussion.