Miaomiao Wen

Social factors that contribute to attrition in MOOCs

In this paper, we explore student dropout behavior in a Massively Open Online Course (MOOC). We use a survival model to measure the impact of three social factors that make predictions about attrition along the way for students who have participated in the course discussion forum.

Exploring the Effect of Confusion in Discussion Forums of Massive Open Online Courses

Thousands of students enroll in Massive Open Online Courses~(MOOCs) to seek opportunities for learning and self-improvement. However, the learning process often involves struggles with confusion, which may have an adverse effect on the course participation experience, leading to dropout along the way. In this paper, we quantify that effect. We describe a classification model using discussion forum behavior and clickstream data to automatically identify posts that express confusion. We then apply survival analysis to quantify the impact of confusion on student dropout. The results demonstrate that the more confusion students express or are exposed to, the lower the probability of their retention. Receiving support and resolution of confusion helps mitigate this effect. We explore the differential effects of confusion expressed in different contexts and related to different aspects of courses. We conclude with implications for design of interventions towards improving the retention of students in MOOCs.

Identifying Latent Study Habits by Mining Learner Behavior Patterns in Massive Open Online Courses

MOOCs attract diverse users with varying habits. Identifying those patterns through clickstream analysis could enable more effective personalized support for student information seeking and learning in that online context. We propose a novel method to characterize types of sessions in MOOCs by mining the habitual behaviors of students within individual sessions. We model learning sessions as a distribution of activities and activity sequences with a topical N-gram model. The representation offers insights into what groupings of habitual student behaviors are associated with higher or lower success in the course. We also investigate how context information, such as time of day or a users demographic information, is associated with the types of learning sessions.

Towards triggering higher-order thinking behaviors in MOOCs

With the aim of better scaffolding discussion to improve learning in a MOOC context, this work investigates what kinds of discussion behaviors contribute to learning. We explored whether engaging in higher-order thinking behaviors results in more learning than paying general or focused attention to course materials. In order to evaluate whether to attribute the effect to engagement in the associated behaviors versus persistent characteristics of the students, we adopted two approaches. First, we used propensity score matching to pair students who exhibit a similar level of involvement in other course activities. Second, we explored individual variation in engagement in higher-order thinking behaviors across weeks. The results of both analyses support the attribution of the effect to the behavioral interpretation. A further analysis using LDA applied to course materials suggests that more social oriented topics triggered richer discussion than more biopsychology oriented topics.

Understanding participant behavior trajectories in online health support groups using automatic extraction methods

This paper presents an automatic analysis method that enables efficient examination of participant behavior trajectories in online communities, which offers the opportunity to examine behavior over time at a level of granularity that has previously only been possible in small scale case study analyses. We provide an empirical validation of its performance. We then illustrate how this method offers insights into behavior patterns that enable avoiding faulty oversimplified assumptions about participation, such as that it follows a consistent trend over time. In particular, we use this method to investigate the connection between user behavior and distressful cancer events and demonstrate how this tool could assist in cancer story summarization.

Towards Identifying the Resolvability of Threads in MOOCs

One important function of the discussion forums of Massive Open Online Courses (MOOCs) is for students to post problems they are unable to resolve and receive help from their peers and instructors. There are a large proportion of threads that are not resolved to the satisfaction of the students for various reasons. In this paper, we attack this problem by firstly constructing a conceptual model validated using a Structural Equation Modeling technique, which enables us to understand the factors that influence whether a problem thread is satisfactorily resolved. We then demonstrate the robustness of these findings using a predictive model that illustrates how accurately those factors can be used to predict whether a thread is resolved or unresolved. Experiments conducted on one MOOC show that thread resolveability connects closely to our proposed five dimensions and that the predictive ensemble model gives better performance over several baselines.

Conversational Metaphors in Use: Exploring the Contrast between Technical and Everyday Notions of Metaphor

Much computational work has been done on identifying and interpreting the meaning of metaphors, but little work has been done on understanding the motivation behind the use of metaphor. To computationally model discourse and social positioning in metaphor, we need a corpus annotated with metaphors relevant to speaker intentions. This paper reports a corpus study as a first step towards computational work on social and discourse functions of metaphor. We use Amazon Mechanical Turk (MTurk) to annotate data from three web discussion forums covering distinct domains. We then compare these to annotations from our own annotation scheme which distinguish levels of metaphor with the labels: nonliteral, conventionalized, and literal. Our hope is that this work raises questions about what new work needs to be done in order to address the question of how metaphors are used to achieve social goals in interaction.

Weakly Supervised Role Identification in Teamwork Interactions

In this paper, we model conversational roles in terms of distributions of turn level behaviors, including conversation acts and stylistic markers, as they occur over the whole interaction. This work presents a lightly supervised approach to inducing role definitions over sets of contributions within an extended interaction, where the supervision comes in the form of an outcome measure from the interaction. The identified role definitions enable a mapping from behavior profiles of each participant in an interaction to limited sized feature vectors that can be used effectively to predict the teamwork outcome. An empirical evaluation applied to two Massive Open Online Course (MOOCs) datasets demonstrates that this approach yields superior performance in learning representations for predicting the teamwork outcome over several baselines.

Virtual Teams in Massive Open Online Courses

Previous work on MOOCs highlights both that the current MOOCs fail to provide the kind of social environment that is desired and that social interaction and exchange of support is important for slowing down attrition over time. However, little is known about how to support virtual teams in a MOOC context. In this paper, we demonstrate what factors distinguish successful and nonsuccessful virtual teams in NovoEd MOOCs, where team collaboration is an integral part of the course design. In particular, we find team leaders play a central role in determining team performance. We discuss implications for continued work towards intelligent support for team leaders in MOOCs.

Discovering habits of effective online support group chatrooms

For users of online support groups, prior research has suggested that a positive social environment is a key enabler of coping. Typically, demonstrating such claims about social interaction would be approached through the lens of sentiment analysis. In this work, we argue instead for a multifaceted view of emotional state, which incorporates both a static view of emotion (sentiment) with a dynamic view based on the behaviors present in a text. We codify this dynamic view through data annotations marking information sharing, sentiment, and coping efficacy. Through machine learning analysis of these annotations, we demonstrate that while sentiment predicts a users stress at the beginning of a chat, dynamic views of efficacy are stronger indicators of stress reduction.