@inproceedings{a796a178094b43669d8882f9b72acd1e,
title = "AI-Powered Resume Feedback: Sentiment and Topic Analysis Using BERT and Transformer Model",
abstract = "This study examines the emotional and thematic patterns in AI-generated resume feedback using BERT-based topic modeling and transformer-based sentiment analysis under happy and gloomy emotional conditions. By exploring how sentiment and thematic content varies in response to prompt-induced emotions, it offers insights into AI-driven career guidance tools. The analysis of sentiment analysis combined with BERT-based topic modeling identified thematic clusters. Paired T-test was employed to assess and compare the emotional responses of participants across gloomy and happy conditions using the validated scale. The results showed consistent thematic structures with minor variations, predominant positivity in feedback (66.58\% positive under happy conditions), and no significant differences in participants' emotional experiences. Findings highlight AI's robustness in providing balanced, emotionally stable feedback for career guidance.",
keywords = "AI-powered resume feedback, BERT-based topic modeling, emotion-induced prompts, sentiment analysis, transformer models",
author = "Shujing Jiang and Wei Wei and Xiangming Li and Lam, \{Chan Tong\}",
note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 5th International Conference on Educational Technology, ICET 2025 ; Conference date: 26-09-2025 Through 28-09-2025",
year = "2025",
doi = "10.1109/ICET67421.2025.11380531",
language = "English",
series = "2025 5th International Conference on Educational Technology, ICET 2025",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "408--413",
booktitle = "2025 5th International Conference on Educational Technology, ICET 2025",
address = "United States",
}