Limits...
Study Partners Recommendation for xMOOCs learners.

Xu B, Yang D - Comput Intell Neurosci (2015)

Bottom Line: Then we proposed a topic model to measure learners' course knowledge awareness.Finally, a social network was constructed based on their activities in the course forum, and the relationship in the network was then employed to recommend study partners for target learner combined with their behavior features and course knowledge awareness.The experiment results show that our method achieves better performance than recommending method only based on content information.

View Article: PubMed Central - PubMed

Affiliation: Computing Center, Northeastern University, Shenyang 110819, China.

ABSTRACT
Massive open online courses (MOOCs) provide an opportunity for people to access free courses offered by top universities in the world and therefore attracted great attention and engagement from college teachers and students. However, with contrast to large scale enrollment, the completion rate of these courses is really low. One of the reasons for students to quit learning process is problems which they face that could not be solved by discussing them with classmates. In order to keep them staying in the course, thereby further improving the completion rate, we address the task of study partner recommendation for students based on both content information and social network information. By analyzing the content of messages posted by learners in course discussion forum, we investigated the learners' behavior features to classify the learners into three groups. Then we proposed a topic model to measure learners' course knowledge awareness. Finally, a social network was constructed based on their activities in the course forum, and the relationship in the network was then employed to recommend study partners for target learner combined with their behavior features and course knowledge awareness. The experiment results show that our method achieves better performance than recommending method only based on content information.

Show MeSH
The number of messages versus the number of students.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4309214&req=5

fig3: The number of messages versus the number of students.

Mentions: In the 10 selected courses, a total of 53,662 messages (including posts and comments) were submitted by 13,064 students who participated in the forum discussion. However, as is shown in Figure 3, nearly 6,000 students submitted only one message. This part of the learners can be seen as nonactive learners. Research shows that the probability of dropout decreased dramatically for those learners who post one or more messages in the forum in first four weeks of the course [6]. Therefore, this paper selects those learners who post less than five messages in the course forum as target users and recommends study partners to them. On the other hand, reducing the recommendation pool will help to improve the efficiency of recommendation. Those learners who have never posted any message in the course forum are not within the scope of this paper because we cannot acquire their learning activities.


Study Partners Recommendation for xMOOCs learners.

Xu B, Yang D - Comput Intell Neurosci (2015)

The number of messages versus the number of students.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4309214&req=5

fig3: The number of messages versus the number of students.
Mentions: In the 10 selected courses, a total of 53,662 messages (including posts and comments) were submitted by 13,064 students who participated in the forum discussion. However, as is shown in Figure 3, nearly 6,000 students submitted only one message. This part of the learners can be seen as nonactive learners. Research shows that the probability of dropout decreased dramatically for those learners who post one or more messages in the forum in first four weeks of the course [6]. Therefore, this paper selects those learners who post less than five messages in the course forum as target users and recommends study partners to them. On the other hand, reducing the recommendation pool will help to improve the efficiency of recommendation. Those learners who have never posted any message in the course forum are not within the scope of this paper because we cannot acquire their learning activities.

Bottom Line: Then we proposed a topic model to measure learners' course knowledge awareness.Finally, a social network was constructed based on their activities in the course forum, and the relationship in the network was then employed to recommend study partners for target learner combined with their behavior features and course knowledge awareness.The experiment results show that our method achieves better performance than recommending method only based on content information.

View Article: PubMed Central - PubMed

Affiliation: Computing Center, Northeastern University, Shenyang 110819, China.

ABSTRACT
Massive open online courses (MOOCs) provide an opportunity for people to access free courses offered by top universities in the world and therefore attracted great attention and engagement from college teachers and students. However, with contrast to large scale enrollment, the completion rate of these courses is really low. One of the reasons for students to quit learning process is problems which they face that could not be solved by discussing them with classmates. In order to keep them staying in the course, thereby further improving the completion rate, we address the task of study partner recommendation for students based on both content information and social network information. By analyzing the content of messages posted by learners in course discussion forum, we investigated the learners' behavior features to classify the learners into three groups. Then we proposed a topic model to measure learners' course knowledge awareness. Finally, a social network was constructed based on their activities in the course forum, and the relationship in the network was then employed to recommend study partners for target learner combined with their behavior features and course knowledge awareness. The experiment results show that our method achieves better performance than recommending method only based on content information.

Show MeSH