%0 Conference Paper %1 citeulike:14346955 %A Boughoula, Assma %A Geigle, Chase %A Zhai, ChengXiang %B Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale %C New York, NY, USA %D 2017 %I ACM %K difficulty las2017 mooc text-analysis topic-modeling web-lecture %P 303--306 %R 10.1145/3051457.3054010 %T A Probabilistic Approach for Discovering Difficult Course Topics Using Clickstream Data %U http://dx.doi.org/10.1145/3051457.3054010 %X One of the main factors affecting the success and effectiveness of Massive Open Online Courses is the ability of the instructor to acquire and incorporate student feedback in a timely manner, and preferably before assigning grades to student assessments. This research uses raw clickstream data from video watching sessions of the Coursera MOOC: "Text Retrieval and Search Engines" to discover which topics are difficult for the students. We introduce a measure for topic difficulty based on these clickstream events, and rank the topics according to this measure. The validity of our ranking is evaluated by comparing it with the ranking of topics based on student votes and find that our method agrees with the ranking based on student votes with > 63\% accuracy. %@ 978-1-4503-4450-0

@inproceedings{citeulike:14346955, abstract = {{One of the main factors affecting the success and effectiveness of Massive Open Online Courses is the ability of the instructor to acquire and incorporate student feedback in a timely manner, and preferably before assigning grades to student assessments. This research uses raw clickstream data from video watching sessions of the Coursera MOOC: "Text Retrieval and Search Engines" to discover which topics are difficult for the students. We introduce a measure for topic difficulty based on these clickstream events, and rank the topics according to this measure. The validity of our ranking is evaluated by comparing it with the ranking of topics based on student votes and find that our method agrees with the ranking based on student votes with > 63\% accuracy.}}, added-at = {2018-03-19T12:24:51.000+0100}, address = {New York, NY, USA}, author = {Boughoula, Assma and Geigle, Chase and Zhai, ChengXiang}, biburl = {https://www.bibsonomy.org/bibtex/2c11977781151852fcede1f63e448a7b2/aho}, booktitle = {Proceedings of the Fourth (2017) ACM Conference on Learning @ Scale}, citeulike-article-id = {14346955}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=3054010}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/3051457.3054010}, doi = {10.1145/3051457.3054010}, interhash = {9def741925b95bedd38ec77678760908}, intrahash = {c11977781151852fcede1f63e448a7b2}, isbn = {978-1-4503-4450-0}, keywords = {difficulty las2017 mooc text-analysis topic-modeling web-lecture}, location = {Cambridge, Massachusetts, USA}, pages = {303--306}, posted-at = {2017-04-29 19:50:05}, priority = {2}, publisher = {ACM}, series = {L@S '17}, timestamp = {2018-03-19T12:24:51.000+0100}, title = {{A Probabilistic Approach for Discovering Difficult Course Topics Using Clickstream Data}}, url = {http://dx.doi.org/10.1145/3051457.3054010}, year = 2017 }