We examine the process of engineering features for developing models that improve our understanding of learners' online behavior in MOOCs. Because feature engineering relies so heavily on human insight, we engage the crowd for feature proposals and guidance on how to operationalize them. When we examined our crowd-sourced features in the context of predicting stopout, not only were they impressively nuanced, but they also integrated more than one interaction mode between the learner and platform and described how the learner was relatively performing.
{"title":"Feature Factory: Crowd Sourced Feature Discovery","authors":"K. Veeramachaneni, Kiarash Adl, Una-May O’Reilly","doi":"10.1145/2724660.2728696","DOIUrl":"https://doi.org/10.1145/2724660.2728696","url":null,"abstract":"We examine the process of engineering features for developing models that improve our understanding of learners' online behavior in MOOCs. Because feature engineering relies so heavily on human insight, we engage the crowd for feature proposals and guidance on how to operationalize them. When we examined our crowd-sourced features in the context of predicting stopout, not only were they impressively nuanced, but they also integrated more than one interaction mode between the learner and platform and described how the learner was relatively performing.","PeriodicalId":20664,"journal":{"name":"Proceedings of the Second (2015) ACM Conference on Learning @ Scale","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75672041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yasmine Kotturi, Chinmay Kulkarni, Michael S. Bernstein, Scott R. Klemmer
When students work with peers, they learn more actively, build richer knowledge structures, and connect material to their lives. However, not every peer learning experience online sees successful adoption. This paper articulates and addresses three adoption challenges for global-scale peer learning. First, peer interactions struggle to bootstrap critical mass. However, class incentives can signal importance and spur initial usage. Second, online classes have limited peer visibility and awareness, so students often feel alone even when surrounded by peers. We find that highlighting interdependence and strengthening norms can mitigate this issue. Third, teachers can readily access "big" aggregate data but not "thick" contextual data that helps build intuitions, so software should guide teachers' scaffolding of peer interactions. We illustrate these challenges through studying 8,500 students' usage of two peer learning platforms, Talkabout and PeerStudio. This paper measures efficacy through sign-up and participation rates and the structure and duration of student interactions.
{"title":"Structure and messaging techniques for online peer learning systems that increase stickiness","authors":"Yasmine Kotturi, Chinmay Kulkarni, Michael S. Bernstein, Scott R. Klemmer","doi":"10.1145/2724660.2724676","DOIUrl":"https://doi.org/10.1145/2724660.2724676","url":null,"abstract":"When students work with peers, they learn more actively, build richer knowledge structures, and connect material to their lives. However, not every peer learning experience online sees successful adoption. This paper articulates and addresses three adoption challenges for global-scale peer learning. First, peer interactions struggle to bootstrap critical mass. However, class incentives can signal importance and spur initial usage. Second, online classes have limited peer visibility and awareness, so students often feel alone even when surrounded by peers. We find that highlighting interdependence and strengthening norms can mitigate this issue. Third, teachers can readily access \"big\" aggregate data but not \"thick\" contextual data that helps build intuitions, so software should guide teachers' scaffolding of peer interactions. We illustrate these challenges through studying 8,500 students' usage of two peer learning platforms, Talkabout and PeerStudio. This paper measures efficacy through sign-up and participation rates and the structure and duration of student interactions.","PeriodicalId":20664,"journal":{"name":"Proceedings of the Second (2015) ACM Conference on Learning @ Scale","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75488208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Saijing Zheng, M. Rosson, Patrick C. Shih, John Millar Carroll
The Massive Open Online Course (MOOC) paradigm has developed rapidly and achieved significant attention from a broad range of populations. However, many people who enroll in MOOCs do not have successful learning experiences. For example, some studies suggest that the relatively weak feelings of community and meager opportunities for collaboration may be contributing to a high dropout rate in MOOCs. In light of such problems, we are exploring new design features that could support enhanced social interactions, collaborative learning and feelings of community. We present our design ideas through a set of activity design scenarios, along with an analysis of possible benefits and negative consequences of our design.
{"title":"Designing MOOCs as Interactive Places for Collaborative Learning","authors":"Saijing Zheng, M. Rosson, Patrick C. Shih, John Millar Carroll","doi":"10.1145/2724660.2728689","DOIUrl":"https://doi.org/10.1145/2724660.2728689","url":null,"abstract":"The Massive Open Online Course (MOOC) paradigm has developed rapidly and achieved significant attention from a broad range of populations. However, many people who enroll in MOOCs do not have successful learning experiences. For example, some studies suggest that the relatively weak feelings of community and meager opportunities for collaboration may be contributing to a high dropout rate in MOOCs. In light of such problems, we are exploring new design features that could support enhanced social interactions, collaborative learning and feelings of community. We present our design ideas through a set of activity design scenarios, along with an analysis of possible benefits and negative consequences of our design.","PeriodicalId":20664,"journal":{"name":"Proceedings of the Second (2015) ACM Conference on Learning @ Scale","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73096675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study investigated the extent to which students asked and instructors answered content-related questions in MOOC discussion forums; subsequently a classification model was built to identify such questions based on extracted linguistic features. Results showed content-related threads were a minority and under-addressed by instructors. However, linguistic modeling was promising in identifying them with high reliability.
{"title":"Identifying Content-Related Threads in MOOC Discussion Forums","authors":"Yi Cui, A. Wise","doi":"10.1145/2724660.2728679","DOIUrl":"https://doi.org/10.1145/2724660.2728679","url":null,"abstract":"This study investigated the extent to which students asked and instructors answered content-related questions in MOOC discussion forums; subsequently a classification model was built to identify such questions based on extracted linguistic features. Results showed content-related threads were a minority and under-addressed by instructors. However, linguistic modeling was promising in identifying them with high reliability.","PeriodicalId":20664,"journal":{"name":"Proceedings of the Second (2015) ACM Conference on Learning @ Scale","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76125313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The design of learning materials and researching their efficacy involves the application of both theoretical learning principles and ways of working or practices to move towards evidence based improvement. This paper abstracts 4 categories from our on-going work of educational technology research which we have found to be important in considering what constitutes a successful Technology-Enhanced Learning implementation. These considerations influence the likelihood or feasibility of the wider adoption a particular Technology-Enhanced Learning implementation in the longer term. We also discuss how these considerations relate to the scalability of the development.
{"title":"Technology-Enhanced Learning: Evidence-based Improvement","authors":"E. Scanlon, T. O'Shea, P. McAndrew","doi":"10.1145/2724660.2728664","DOIUrl":"https://doi.org/10.1145/2724660.2728664","url":null,"abstract":"The design of learning materials and researching their efficacy involves the application of both theoretical learning principles and ways of working or practices to move towards evidence based improvement. This paper abstracts 4 categories from our on-going work of educational technology research which we have found to be important in considering what constitutes a successful Technology-Enhanced Learning implementation. These considerations influence the likelihood or feasibility of the wider adoption a particular Technology-Enhanced Learning implementation in the longer term. We also discuss how these considerations relate to the scalability of the development.","PeriodicalId":20664,"journal":{"name":"Proceedings of the Second (2015) ACM Conference on Learning @ Scale","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74056926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nakull Gupta, J. O'Neill, A. Cross, Edward Cutrell, W. Thies
While most MOOCs rely on world-famous experts to teach the masses, in many circumstances students may learn more from people who share their context such as local teachers or peers. Here, we describe an experiment to explore how the "source" of video content, the teacher, affects online learning, specifically in the context of higher education in Indian colleges. The proposed experiment will compare three content sources -- a local lecturer (teacher from an Indian engineering college), a local peer (both male and female students similar to the targeted audience), and an internationally recognized expert (a Stanford lecturer). Students will watch videos by the various source authors, after which we will measure differences in their preference, engagement, and learning. In addition, we discuss our experiences with helping students prepare video lectures and describe the support and processes we used to curate interesting and clear peer-generated content.
{"title":"Source Effects in Online Education","authors":"Nakull Gupta, J. O'Neill, A. Cross, Edward Cutrell, W. Thies","doi":"10.1145/2724660.2728671","DOIUrl":"https://doi.org/10.1145/2724660.2728671","url":null,"abstract":"While most MOOCs rely on world-famous experts to teach the masses, in many circumstances students may learn more from people who share their context such as local teachers or peers. Here, we describe an experiment to explore how the \"source\" of video content, the teacher, affects online learning, specifically in the context of higher education in Indian colleges. The proposed experiment will compare three content sources -- a local lecturer (teacher from an Indian engineering college), a local peer (both male and female students similar to the targeted audience), and an internationally recognized expert (a Stanford lecturer). Students will watch videos by the various source authors, after which we will measure differences in their preference, engagement, and learning. In addition, we discuss our experiences with helping students prepare video lectures and describe the support and processes we used to curate interesting and clear peer-generated content.","PeriodicalId":20664,"journal":{"name":"Proceedings of the Second (2015) ACM Conference on Learning @ Scale","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79141193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wheel-spinning refers to a phenomenon in which a student has spent a considerable amount of time practicing a skill, yet displays little or no progress towards mastery. Wheel-spinning has been shown to be a common problem affecting a significant number of students in different tutoring systems and is negatively associated with learning. In this study, we construct a model of wheel-spinning, using generic features easily calculated from most tutoring systems. We show that for two different systems' data, the model generalizes to future students very well and can detect wheel-spinning in an early stage with high accuracy. We also refine the scope of the wheel-spinning problem in two systems using the model's predictions.
{"title":"Towards Detecting Wheel-Spinning: Future Failure in Mastery Learning","authors":"Yue Gong, J. Beck","doi":"10.1145/2724660.2724673","DOIUrl":"https://doi.org/10.1145/2724660.2724673","url":null,"abstract":"Wheel-spinning refers to a phenomenon in which a student has spent a considerable amount of time practicing a skill, yet displays little or no progress towards mastery. Wheel-spinning has been shown to be a common problem affecting a significant number of students in different tutoring systems and is negatively associated with learning. In this study, we construct a model of wheel-spinning, using generic features easily calculated from most tutoring systems. We show that for two different systems' data, the model generalizes to future students very well and can detect wheel-spinning in an early stage with high accuracy. We also refine the scope of the wheel-spinning problem in two systems using the model's predictions.","PeriodicalId":20664,"journal":{"name":"Proceedings of the Second (2015) ACM Conference on Learning @ Scale","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80038033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Markus Krause, M. Mogalle, Henning Pohl, J. Williams
Many MOOCs report high drop off rates for their students. Among the factors reportedly contributing to this picture are lack of motivation, feelings of isolation, and lack of interactivity in MOOCs. This paper investigates the potential of gamification with social game elements for increasing retention and learning success. Students in our experiment showed a significant increase of 25% in retention period (videos watched) and 23% higher average scores when the course interface was gamified. Social game elements amplify this effect significantly -- students in this condition showed an increase of 50% in retention period and 40% higher average test scores.
{"title":"A Playful Game Changer: Fostering Student Retention in Online Education with Social Gamification","authors":"Markus Krause, M. Mogalle, Henning Pohl, J. Williams","doi":"10.1145/2724660.2724665","DOIUrl":"https://doi.org/10.1145/2724660.2724665","url":null,"abstract":"Many MOOCs report high drop off rates for their students. Among the factors reportedly contributing to this picture are lack of motivation, feelings of isolation, and lack of interactivity in MOOCs. This paper investigates the potential of gamification with social game elements for increasing retention and learning success. Students in our experiment showed a significant increase of 25% in retention period (videos watched) and 23% higher average scores when the course interface was gamified. Social game elements amplify this effect significantly -- students in this condition showed an increase of 50% in retention period and 40% higher average test scores.","PeriodicalId":20664,"journal":{"name":"Proceedings of the Second (2015) ACM Conference on Learning @ Scale","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77511472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study investigates chat room data from a massive open online course (MOOC) that has been organized several times since January 2012. What makes the organization unique is that the chat room has always remained the same, allowing past participants to mingle with the new course takers. Participants who have previously attended the course have started to support the novices, voluntarily taking the role of mentors, while at the same time also learning themselves. Two and a half years of chat logs and interviews show that it is possible that a community consisting of previous and current participants emerges naturally. Furthermore, there are plenty of students that unconditionally help others, even when they themselves no longer attend the course. Our observations suggest that communities of practice emerge naturally around the chat rooms of MOOCs.
{"title":"Alumni & Tenured Participants in MOOCs: Analysis of Two Years of MOOC Discussion Channel Activity","authors":"Matti Nelimarkka, Arto Vihavainen","doi":"10.1145/2724660.2724671","DOIUrl":"https://doi.org/10.1145/2724660.2724671","url":null,"abstract":"This study investigates chat room data from a massive open online course (MOOC) that has been organized several times since January 2012. What makes the organization unique is that the chat room has always remained the same, allowing past participants to mingle with the new course takers. Participants who have previously attended the course have started to support the novices, voluntarily taking the role of mentors, while at the same time also learning themselves. Two and a half years of chat logs and interviews show that it is possible that a community consisting of previous and current participants emerges naturally. Furthermore, there are plenty of students that unconditionally help others, even when they themselves no longer attend the course. Our observations suggest that communities of practice emerge naturally around the chat rooms of MOOCs.","PeriodicalId":20664,"journal":{"name":"Proceedings of the Second (2015) ACM Conference on Learning @ Scale","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87547608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A large amount of research in the field of educational data analytics has focused primarily on student next problem correctness. Although the prediction of such information is useful in assessing current student performance, it is better for teachers and instructors to place attention on student knowledge over a longer period of time. Several researchers have articulated that it is important to predict aspects that are more meaningful, inspiring our work here to utilize the large amounts of student data available to derive more substantial predictions over student knowledge. Our goal in this paper is to utilize prerequisite information to better predict student knowledge quantitatively as a subsequent skill is begun. Learning systems like ASSISTments and Khan Academy already record such prerequisite information, and can therefore be used to construct a method of prediction as described in this paper. Using these inter-skill relationships, our method estimates students' initial knowledge based on performance on each prerequisite skill. We compare our method with the standard Knowledge Tracing (KT) model and majority class in terms of the predictive accuracy of students' first responses on subsequent skills. Our results support our method as a viable means of representing student prerequisite knowledge in a subsequent skill, leading to results that outperform the majority class and that are comparably superior to KT by providing more definitive student knowledge estimates without sacrificing predictive accuracy.
{"title":"The Prediction of Student First Response Using Prerequisite Skills","authors":"Anthony F. Botelho, Hao Wan, N. Heffernan","doi":"10.1145/2724660.2724675","DOIUrl":"https://doi.org/10.1145/2724660.2724675","url":null,"abstract":"A large amount of research in the field of educational data analytics has focused primarily on student next problem correctness. Although the prediction of such information is useful in assessing current student performance, it is better for teachers and instructors to place attention on student knowledge over a longer period of time. Several researchers have articulated that it is important to predict aspects that are more meaningful, inspiring our work here to utilize the large amounts of student data available to derive more substantial predictions over student knowledge. Our goal in this paper is to utilize prerequisite information to better predict student knowledge quantitatively as a subsequent skill is begun. Learning systems like ASSISTments and Khan Academy already record such prerequisite information, and can therefore be used to construct a method of prediction as described in this paper. Using these inter-skill relationships, our method estimates students' initial knowledge based on performance on each prerequisite skill. We compare our method with the standard Knowledge Tracing (KT) model and majority class in terms of the predictive accuracy of students' first responses on subsequent skills. Our results support our method as a viable means of representing student prerequisite knowledge in a subsequent skill, leading to results that outperform the majority class and that are comparably superior to KT by providing more definitive student knowledge estimates without sacrificing predictive accuracy.","PeriodicalId":20664,"journal":{"name":"Proceedings of the Second (2015) ACM Conference on Learning @ Scale","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2015-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83000372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：