Mining for gold: Identifying content-related MOOC discussion threads across domains through linguistic modeling

详细信息    查看全文

• 作者：Alyssa Friend Wise^a ; ^{alyssa.wise@nyu.edu} ; Yi Cui^b ; ^{yca231@sfu.ca} ; WanQi Jin^b ; ^{wanqij@sfu.ca} ; Jovita Vytasek^b ; ^{jvytasek@sfu.ca}
• 关键词：Massive open online courses ; Social interaction ; Discussion forums ; Natural language processing ; Computer-mediated communication ; Content analysis
• 刊名：The Internet and Higher Education
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：32
• 期：Complete
• 页码：11-28
• 全文大小：1556 K
• 卷排序：32

文摘

Content-related threads in MOOC discussions have distinct linguistic features. Linguistic modeling can reliably identify content-related starting posts and replies. Most top linguistic features appear to be unrelated to the course domain. The number of views and votes threads received were not helpful for classification.