Leveraging Large Language Models for Sentiment Analysis in Educational Contexts.

Area of Science:

• Educational Technology
• Artificial Intelligence
• Natural Language Processing

Background:

• Traditional sentiment analysis methods struggle with nuanced qualitative data.
• Understanding student emotions is crucial for effective educational interventions.

Purpose of the Study:

• To explore the efficacy of Large Language Models (LLMs) for sentiment analysis in educational contexts.
• To assess student emotional states and attitudes towards academic performance using LLM-driven analysis of student reports.

Main Methods:

• Qualitative analysis of student reports using Large Language Models (LLMs).
• Sentiment analysis to gauge emotional states and attitudes.
• Comparison of LLM-based analysis with traditional coding methods.

Main Results:

• LLMs effectively processed and analyzed textual data from student reports.
• Sentiment analysis provided nuanced insights into student engagement and areas needing attention.
• LLM approach offered a more detailed understanding of student sentiments than traditional methods.

Conclusions:

• Large Language Models (LLMs) demonstrate significant potential for sentiment analysis in education.
• LLM application can enhance the depth and accuracy of educational assessments.
• This technology may facilitate more targeted and effective educational interventions.