Gender Prediction of Generated Tweets Using Generative AI

Abstract

With the use of Generative AI (GenAI), Online Social Networks (OSNs) now generate a huge volume of content data. Yet, user-generated content on OSNs, aided by GenAI, presents challenges in analyzing and understanding its characteristics. In particular, tweets generated by GenAI at the request of authentic human users present difficulties in determining the gendered variation of the content. The vast amount of data generated from tweets’ content necessitates a thorough investigation into the gender-specific language used in these tweets. This study explores the task of predicting the gender of text content in tweets generated by GenAI. Through our analysis and experimentation, we have achieved a remarkable 90% accuracy in attributing gender-specific language to these tweets. Our research not only highlights the potential of GenAI in gender prediction but also underscores the sophisticated techniques employed to decipher the refined linguistic cues that differentiate male and female language in GenAI-generated content. This advancement in understanding and predicting gender-specific language in GenAI-generated tweets covers the way for more refined and accurate content analysis in the evolving landscape of OSNs.

Keywords

• generative AI
• artificial intelligence
• linguistic patterns
• text classification
• GenAI-generated
• human authored