Hayat, A., & Khan, B., & Hasan, M. R. (2025, June), BOARD # 288: NSF: IUSE Harnessing Language Models to Predict and Enhance STEM Engagement Using Non-Cognitive Experiential Data  Paper presented at 2025 ASEE Annual Conference & Exposition , Montreal, Quebec, Canada . 10.18260/1-2--55652

\bibitem{asee_peer_55652}
  Hayat, A., \& Khan, B., \& Hasan, M. R. (2025, June), \emph{BOARD \# 288: NSF: IUSE Harnessing Language Models to Predict and Enhance STEM Engagement Using Non-Cognitive Experiential Data}
  Paper presented at 2025 ASEE Annual Conference \& Exposition , Montreal, Quebec, Canada .
  10.18260/1-2--55652

Ahatsham Hayat, Bilal Khan, and Mohammad Rashedul Hasan.  "BOARD # 288: NSF: IUSE Harnessing Language Models to Predict and Enhance STEM Engagement Using Non-Cognitive Experiential Data".  2025 ASEE Annual Conference & Exposition , Montreal, Quebec, Canada , 2025, June.  ASEE Conferences, 2025.  https://peer.asee.org/55652 Internet.  29 Aug, 2025

\bibitem{asee_peer_55652}
  Ahatsham Hayat, Bilal Khan, and Mohammad Rashedul Hasan.
  "BOARD \# 288: NSF: IUSE Harnessing Language Models to Predict and Enhance STEM Engagement Using Non-Cognitive Experiential Data".
  \emph{2025 ASEE Annual Conference \& Exposition , Montreal, Quebec, Canada , 2025, June}.
  ASEE Conferences, 2025.
  https://peer.asee.org/55652 Internet.  29 Aug, 2025

@INPROCEEDINGS{asee_peer_55652
author = "Ahatsham Hayat, Bilal Khan, and Mohammad Rashedul Hasan"
title = "BOARD \# 288: NSF: IUSE Harnessing Language Models to Predict and Enhance STEM Engagement Using Non-Cognitive Experiential Data"
booktitle = "2025 ASEE Annual Conference \& Exposition "
year = "2025"
month = "June"
address = "Montreal, Quebec, Canada "
publisher = "ASEE Conferences"
note = {https://peer.asee.org/55652}
number = {10.18260/1-2--55652}
}

TY  - CPAPER
AB  - This research explores the use of pre-trained large language models (LLMs) to predict weekly lecture-based engagement of college STEM students based on longitudinal experiential data. We leverage non-cognitive attributes, such as emotional responses, and socio-economic background information to forecast engagement patterns. To address data limitations, we employ a contextual data enrichment method. Experiments with BERT (encoder-only) and Llama (decoder-only) models demonstrate that BERT achieves higher accuracy, particularly with non-cognitive data, while both models improve with background data integration. These findings highlight LLMs' potential to enable data-driven interventions in STEM education by predicting student engagement.
AU  - Ahatsham Hayat
AU  - Bilal Khan
AU  - Mohammad Rashedul Hasan
CY  - Montreal, Quebec, Canada 
DA  - 2025/06/22
PB  - ASEE Conferences
TI  - BOARD # 288: NSF: IUSE Harnessing Language Models to Predict and Enhance STEM Engagement Using Non-Cognitive Experiential Data
UR  - https://peer.asee.org/55652
DO  - 10.18260/1-2--55652
ER  -