Improving MOOCs Using Information From Discussion Forums: An Opinion Summarization and Suggestion Mining Approach

Abstract

Discussion forums are integral to MOOCs and a useful resource for collaborative learning. In this paper we examine if the the posts made on forums by participants can also provide meaningful information to assess and improve the effectiveness of MOOCs. We present an empirical approach that uses posts in MOOC forums to summarize participants' opinion towards aspects of a course and identify suggestions for improving a course. Specifically, our approach: (1) detects participants' attitude towards aspects of a course (e.g. professor, lecture, assignment) at a context or sentence level, (2) extracts suggestions for course improvement, which is a novel space in MOOC learning analytics, and (3) aggregates and displays the results visually. The study used lexicon and rule-based approach and was able to identify aspect-based sentiments and suggestions related to course design elements with a good overall score (0.41 kappa score). By summarizing opinions from a vast amount of textual data on forums our approach allows instructors to improve their course and thereby student engagement and learning.

Learning analytics driven improvements in learning design in higher education: A systematic literature review

“…These studies employed a data‐driven, ‘down‐top’ approach (Rodríguez‐Triana et al, 2015): the researchers approached the LA‐LD integration based on the available course data (e.g., Hung et al, 2017). Often, LA in these studies was used to generally support stakeholders, without certain pedagogical intentions (e.g., Almatrafi & Johri, 2022). The LA tool is integrated into the course (33 papers).…”

“…It seems only logical that researchers approached LA‐LD related issues referring to engagement (de Leng & Pawelka, 2020; Fan et al, 2021, etc. ), motivation (Hung et al, 2017), self‐regulated learning (Estévez‐Ayres et al, 2017), social learning (Almatrafi & Johri, 2022; Haya et al, 2015), social constructivism (Er et al, 2019), constructionism (Haya et al, 2015), cognitivism (Davies et al, 2021; Rayyan et al, 2016), praxeology educology (Frick et al, 2022), visualisation theory (de Leng & Pawelka, 2020), social comparison theory (Kokoç & Altun, 2021), and so forth. It is important to note that certain publications that went more deeply into the issue of LA‐LD theoretical background were not included in the final selection owing to their theoretical nature or lack of empirical evidence.…”

“…The main focus areas were student behaviour, satisfaction, and performance (Rienties et al, 2017). Then, research indicated that LA could benefit collaborative learning (Almatrafi & Johri, 2022;Rafique et al, 2021); self-reflection of students (Kitto et al, 2017;Knight et al, 2018); student interaction with tools (Kokoç & Altun, 2021), and so forth. Next, teaching was brought to the forefront of the debate.…”

“…It seems only logical that researchers approached LA-LD related issues referring to engagement (deLeng & Pawelka, 2020; Fan et al, 2021, etc. ), motivation(Hung et al, 2017), self-regulated learning(Estévez-Ayres et al, 2017), social learning(Almatrafi & Johri, 2022;Haya et al, 2015), social constructivism(Er et al, 2019),…”

Opinion texts summarization based on texts concepts with multi-objective pruning approach

“…As noted earlier, the goal in the summarization of opinion texts is to receive a set of opinions expressed on a social network to create a useful summary that includes the content of the majority of initial texts [ 1 , 12 , 13 ]. Summarizing the opinions and sentiments expressed on social networks is a cutting-edge research area where a large number of studies have been performed to enhance linguistic quality and reduce the redundancy of summarization methods.…”