Emotion and Associated Topic Detection for Course Comments in a MOOC Platform

Liu, Zhi; Zhang, Wenjing; Sun, Jianwen; Cheng, Hercy N.H.; Peng, Xian; Liu, Sanya

doi:10.1109/eitt.2016.11

Cited by 32 publications

(23 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…On the other hand, comments have been studied in many setups, including MOOCs. [14] emphasises the importance of using machine learning methods to analyse MOOCs comments, to detect the emotions of learners and predict the popularity of each course. [15] focused on grouping students based on their preferences, by conducting an online pre-course survey.…”

Section: Related Researchmentioning

confidence: 99%

On the Need for Fine-Grained Analysis of Gender Versus Commenting Behaviour in MOOCs

Alshehri

Foss

Cristea

et al. 2018

Proceedings of the 2018 the 3rd International Conference on Information and Education Innovations - ICIEI 2018

View full text Add to dashboard Cite

Stereotyping is the first type of adaptation ever proposed. However, the early systems have never dealt with the numbers of learners that current Massive Open Online Courses (MOOCs) provide. Thus, the umbrella question that this work tackles is if learner characteristics can predict their overall, but also fine-grain behaviour. Earlier results point at differences related to gender or to age. Here, we analyse gender versus commenting behaviour. Our fine-grained analysis shows that the result may further depend on the course topic, or even week. Surprisingly, for instance, women chat less in a Psychology-related course, but more (or similar) on a Computer Science course. These results are analysed in this paper in details, including two different methods of averaging comments, leading to remarkably different results. The outcomes can help in informing future runs, in terms of potential personalised feedback for teachers and students.

show abstract

Section: Related Researchmentioning

confidence: 99%

On the Need for Fine-Grained Analysis of Gender Versus Commenting Behaviour in MOOCs

Alshehri

Foss

Cristea

et al. 2018

Proceedings of the 2018 the 3rd International Conference on Information and Education Innovations - ICIEI 2018

View full text Add to dashboard Cite

show abstract

“…On the other hand, comments have been studied in many setups, including MOOCs. [13] emphasises the importance of using machine learning methods to analyse MOOCs comments, in order to detect the emotions of learners and predict the popularity of each course. [14] focused on grouping students based on their preferences by conducting an online pre-course survey.…”

Section: Related Researchmentioning

confidence: 99%

Can learner characteristics predict their behaviour on MOOCs?

Cristea

Alamri

Alshehri

et al. 2018

Proceedings of the 10th International Conference on Education Technology and Computers

View full text Add to dashboard Cite

The full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. ABSTRACTStereotyping is the first type of adaptation in education ever proposed. However, the early systems have never dealt with the numbers of learners that current MOOCs provide. Thus, the umbrella question that this work tackles is if learner characteristics can predict their overall, but also fine-grain behaviour. Earlier results point at differences related to gender or to age. However, our finer-grain analysis shows that the result may further depend on the course topic, or even week. Surprisingly, for instance, women chat less in a Psychology-related course, but more (or similar) on a Computer Science course. These results are analysed in this paper in details, including different methods of averaging comments, leading to surprisingly different results. The outcomes can help in informing future runs, in terms of potential personalised feedback for teachers and students.

show abstract

“…Massive Open Online Courses (MOOCs) bring together a large number of students, whose platforms store the data generated by navigation and interactions -which can be used for many types os researches, making it possible to detect problems and make decisions that contribute to improve teaching and learning experiences online (Liu et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

“…Affection in MOOCs were underexplored in online courses, because they contain a variety of non-directly accessible behavioral information, which makes it a challenging type of information to extract , but have been receiving increassing attention because of the effects positive and negative emotions have in learning (Tzeet al, 2017). If in the context of classroom teaching the students' emotions are more visible to the teacher, in MOOCs -where there is often no interference from teachers or tutors -this identification becomes much more subtle (Liu et al, 2016;Rothkrantz, 2017).…”

Section: Introductionmentioning

confidence: 99%

Identification of Affective States in MOOCs

Souza

Perry

2018

Int J Innov Educ Res

View full text Add to dashboard Cite

Massive Open Online Courses (MOOCs) are a type of online coursewere students have little interaction, no instructor, and in some cases, no deadlines to finisch assignments. For this reason, a better understanding of student affection in MOOCs is importantant could have potential to open new perspectives for this type of course. The recent popularization of tools, code libraries and algorithms for intensive data analysis made possible collect data from text and interaction with the platforms, which can be used to infer correlations between affection and learning. In this context, a bibliographical review was carried out, considering the period between 2012 and 2018, with the goal of identifying which methods are being to identify affective states. Three databases were used: ACM Digital Library, IEEE Xplore and Scopus, and 46 papers were found. The articles revealed that the most common methods are related to data intensive techinques (i.e. machine learning, sentiment analysis and, more broadly, learning analytics). Methods such as physiological signal recognition andself-report were less frequent.

show abstract

Emotion and Associated Topic Detection for Course Comments in a MOOC Platform

Cited by 32 publications

References 8 publications

On the Need for Fine-Grained Analysis of Gender Versus Commenting Behaviour in MOOCs

On the Need for Fine-Grained Analysis of Gender Versus Commenting Behaviour in MOOCs

Can learner characteristics predict their behaviour on MOOCs?

Identification of Affective States in MOOCs

Contact Info

Product

Resources

About