Bringing order to chaos in MOOC discussion forums with content-related thread identification

Wise, Alyssa Friend; Cui, Yi; Vytasek, Jovita M.

doi:10.1145/2883851.2883916

Cited by 50 publications

(28 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such keywords as "difference between" have been characterised by Daems et al [6] as "signal concepts". Our overall distinction between types of indicators for certain categories of contributions has also been inspired by Wise and Cui's findings on the identification of forum threads related to the course content using indicator phrases [28]. Additionally, we also identify resource related keywords mentioning course material, i.e.…”

Section: Methodsmentioning

confidence: 94%

“…The types and themes of discussion forums can be very diverse and are not necessarily related to the actual course subject [20], for example, non-course subject related discussions like search for learning groups or personal introductions, technical and organisational support. Since collaborative knowledge building and information exchange is of great interest Wise and Cui [28] proposed content-based indicators for subject related discussions. Similarly, Rossi et al [23] build supervised classifiers to predict the type of discussion of forum threads.…”

Section: Related Workmentioning

confidence: 99%

“…For this reason, analyses of MOOCs discussion forums have received much attention in recent years. Previous studies in the literature have investigated discussion forums from different perspectives such as learners engagement and activities [15,20,1], discussion themes and topics or linguistic properties of written messages [28,23,16], structure of the communication network, group formation and social interactions among forum participants [9,10,19]. A detailed overview of previous works on forum analysis is presented in section 2.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamics of MOOC discussion forums

Boroujeni¹,

Hecking

Hoppe

et al. 2017

Proceedings of the Seventh International Learning Analytics &Amp; Knowledge Conference

View full text Add to dashboard Cite

In this integrated study of dynamics in MOOCs discussion forums, we analyze the interplay of temporal patterns, discussion content, and the social structure emerging from the communication using mixed methods. A special focus is on the yet under-explored aspect of time dynamics and influence of the course structure on forum participation. Our analyses show dependencies between the course structure (video opening time and assignment deadlines) and the overall forum activity whereas such a clear link could only be partially observed considering the discussion content. For analyzing the social dimension we apply role modeling techniques from social network analysis. While the types of user roles based on connection patterns are relatively stable over time, the high fluctuation of active contributors lead to frequent changes from active to passive roles during the course. However, while most users do not create many social connections they can play an important role in the content dimension triggering discussions on the course subject. Finally, we show that forum activity level can be predicted one week in advance based on the course structure, forum activity history and attributes of the communication network which enables identification of periods when increased tutor supports in the forum is necessary.

show abstract

Section: Methodsmentioning

confidence: 94%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamics of MOOC discussion forums

Boroujeni¹,

Hecking

Hoppe

et al. 2017

Proceedings of the Seventh International Learning Analytics &Amp; Knowledge Conference

View full text Add to dashboard Cite

show abstract

“…Research in predicting drop-out using features hand-engineered from the clickstream have used SVMs [6], logistic regression [7], Hidden Markov Models [8], ensembles of other machine learning methods [9], and recurrent neural networks (RNN) applied to hand engineered features [5]. Other work has included information outside the clickstream, such as forum post data analyzed with natural language processing [10,17]. Frameworks for evaluating various models and their feature sets have also been introduced [15,22].…”

Section: Related Workmentioning

confidence: 99%

Communication at Scale in a MOOC Using Predictive Engagement Analytics

Pardos

Meyer

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

“…A crucial step in the analysis of forum discussions in online courses is the identification of the discussion threads relevant for course-related information exchange between participants. In a recent study (Wise, Cui, & Vytasek, 2016), a combination of content analysis and machine learning was used to distinguish forum threads in which participants discuss the course content from those merely socializing or discussing organizational matters. Content analysis is also used to characterize forum users based on the types of contributions they make (Arguello & Shaffer, 2015;Liu, Kidzinski, & Dillenbourg, 2015).…”

Section: Background and Related Workmentioning

confidence: 99%

Role Modelling in MOOC Discussion Forums

2017

View full text Add to dashboard Cite

ABSTRACT:To further develop rich and expressive ways of modelling roles of contributors in discussion forums of online courses, particularly in MOOCs, networks of forum users are analyzed based on the relations of information-giving and information-seeking. Specific connection patterns that appear in the information exchange networks of forum users are used to characterize user roles. Additionally, semantic roles are derived by identifying thematic areas in which an actor (learner) looks for information (problem areas) and the areas of interest in which an actor provides information to others (areas of expertise). The interplay of social and semantic roles is analyzed using a socio-semantic blockmodelling approach. The results indicate that social and semantic roles are not strongly interdependent. The methodological contribution is in combining traditional blockmodelling with semantic information to characterize participant roles. Furthermore, we use sequential pattern analysis techniques to analyze the posting activity of users over time in terms of categories of cognitive engagement. The combination of the different approaches reveals that user roles derived from the analysis of engagement patterns are strongly related to socio-semantic user roles.

show abstract

Bringing order to chaos in MOOC discussion forums with content-related thread identification

Cited by 50 publications

References 15 publications

Dynamics of MOOC discussion forums

Dynamics of MOOC discussion forums

Communication at Scale in a MOOC Using Predictive Engagement Analytics

Role Modelling in MOOC Discussion Forums

Contact Info

Product

Resources

About