کنفرانس مهندسی برق ایران

صفحه اصلی / سی و سومین کنفرانس بین المللی مهندسی برق

Decoding Trait: Using Dual Transformers to Analyze Gender, Age Range and Personality

نویسندگان :

ُSaeed Asadian¹ Mostafa Tanasan² Bijan Vosoughi vahdat³

1- دانشگاه صنعتی شریف 2- دانشگاه صنعتی شریف 3- دانشگاه صنعتی شریف

کلمات کلیدی :

Author Profiling،Gender Detection،Age Range Classification،Personality Type Assessment،X Social Media Data،Dual Transformers Mechanism

چکیده :

Author profiling involves analyzing text produced by individuals to discern their demographic traits and characteristics. With the proliferation of textual data on social networks, this research aims to demonstrate how Persian-language content reflects an individual's attributes, including gender, age range, and personality type. We collected data from a specific social media platform using targeted keywords related to these traits. Gender detection is framed as a binary classification problem, while age detection involves three classes, and personality detection, based on the Myers–Briggs Type Indicator (MBTI) framework, consists of four binary classification tasks. A key challenge in analyzing social media data is the fragmented nature of user tweets. To address this issue, we propose a dual transformers mechanism. Finally, we evaluate our proposed model, and the results indicate its efficacy in comparison to baseline methods.