Learning in Massive Open Online Courses:Evidence from Social Media Mining

• Main Authors: Chin-Jin Guo, 郭金鈤
• Other Authors: Chien-wen Shen
• Format: Others
• Language: zh-TW
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/07029258789006125763

博士 === 國立中央大學 === 企業管理學系 === 103 === Many massive open online courses(MOOCs)have adopted social media tools for large student audiences to co-create knowledge and engage in collective learning processes. To further understand the public opinion toward MOOCs learning, this study adopted various social media mining approaches to investigate Twitter messages. An analysis of the descriptive statistics and trends of MOOC-related Twitter messages revealed that MOOC-related discussions on Twitter were 5-fold more active on weekdays than at the weekend. A monthly analysis on Twitter showed that October was the most active month of the year, whereas August was the least active month. Therefore, MOOC practitioners should focus on MOOC discussions during peak periods to respond immediately to student feedback. In addition, the results of a sentiment analysis involving observations of monthly activities on Twitter indicated that public opinion toward MOOCs was slightly negative, although there were generally more positive messages about learning through MOOCs than there were negative ones. Therefore, MOOC practitioners should investigate negative Twitter messages related to MOOCs to understand the underlying reasons for them. When MOOCs communities discuss specific news topics, MOOC practitioners can investigate the difference between the number of positive and negative tweets on a given day to understand public opinion toward the news. Furthermore, our findings regarding the influencers of MOOCs retweets indicate that the top 5%–10% of influencers typically account for 50% of sentimental retweets about MOOCs. Social network diagrams were also developed to reveal how sentimental messages about MOOCs on Twitter were disseminated from the top influencers with the highest number of positive/negative retweets about MOOCs. The MOOCs were generally disseminated to a maximum of 2 layers of users in Twitter social networks. Our findings of social media mining show that Twitter can assist MOOC practitioners in improving their understanding of the insights of MOOCs to effectively improve student learning.