An Automated Text Summarization Approach for Open-ended Responses in Student Online Surveys

Student satisfaction is a crucial aspect of online and distance academic education, often linked to academic achievement and attrition rates. Student satisfaction in academic settings is measured mostly with questionnaires, typically consisting of closed-ended questions, while open-ended questions are rarely used. The richness of qualitative data collected by open-ended responses can reveal hidden aspects of the educational process and guide academic stakeholders' decision-making more effectively. However, analyzing qualitative data is a challenge, especially when the collected data are large. This study aims to detect Hellenic Open University's (HOU) student satisfaction with distance academic education using an automated text summarization method for analyzing their written comments in an online questionnaire. The sample consisted of students who attended a postgraduate module in the first semester of the academic year 2023–2024. The findings show that students are satisfied with tutor-student interaction, online student-tutor meetings, and educational activities. However, some students are dissatisfied with how time is allocated between educational materials and activities, suggesting a need for better alignment in future sessions. Regarding the methods used, auto-summarization has proven to be less time-consuming compared to human summarization, though it requires thorough data preparation to be effective.