Yi-Chia Wang

Analyzing collaborative learning processes automatically: Exploiting the advances of computational linguistics in computer-supported collaborative learning.

In this article we describe the emerging area of text classification research focused on the problem of collaborative learning process analysis both from a broad perspective and more specifically in terms of a publicly available tool set called TagHelper tools. Analyzing the variety of pedagogically valuable facets of learners’ interactions is a time consuming and effortful process. Improving automated analyses of such highly valued processes of collaborative learning by adapting and applying recent text classification technologies would make it a less arduous task to obtain insights from corpus data. This endeavor also holds the potential for enabling substantially improved on-line instruction both by providing teachers and facilitators with reports about the groups they are moderating and by triggering context sensitive collaborative learning support on an as-needed basis. In this article, we report on an interdisciplinary research project, which has been investigating the effectiveness of applying text classification technology to a large CSCL corpus that has been analyzed by human coders using a theory-based multi-dimensional coding scheme. We report promising results and include an in-depth discussion of important issues such as reliability, validity, and efficiency that should be considered when deciding on the appropriateness of adopting a new technology such as TagHelper tools. One major technical contribution of this work is a demonstration that an important piece of the work towards making text classification technology effective for this purpose is designing and building linguistic pattern detectors, otherwise known as features, that can be extracted reliably from texts and that have high predictive power for the categories of discourse actions that the CSCL community is interested in.

Eliciting and Receiving Online Support: Using Computer-Aided Content Analysis to Examine the Dynamics of Online Social Support

Background Although many people with serious diseases participate in online support communities, little research has investigated how participants elicit and provide social support on these sites. Objective The first goal was to propose and test a model of the dynamic process through which participants in online support communities elicit and provide emotional and informational support. The second was to demonstrate the value of computer coding of conversational data using machine learning techniques (1) by replicating results derived from human-coded data about how people elicit support and (2) by answering questions that are intractable with small samples of human-coded data, namely how exposure to different types of social support predicts continued participation in online support communities. The third was to provide a detailed description of these machine learning techniques to enable other researchers to perform large-scale data analysis in these communities. Methods Communication among approximately 90,000 registered users of an online cancer support community was analyzed. The corpus comprised 1,562,459 messages organized into 68,158 discussion threads. Amazon Mechanical Turk workers coded (1) 1000 thread-starting messages on 5 attributes (positive and negative emotional self-disclosure, positive and negative informational self-disclosure, questions) and (2) 1000 replies on emotional and informational support. Their judgments were used to train machine learning models that automatically estimated the amount of these 7 attributes in the messages. Across attributes, the average Pearson correlation between human-based judgments and computer-based judgments was .65. Results Part 1 used human-coded data to investigate relationships between (1) 4 kinds of self-disclosure and question asking in thread-starting posts and (2) the amount of emotional and informational support in the first reply. Self-disclosure about negative emotions (beta=.24, P<.001), negative events (beta=.25, P<.001), and positive events (beta=.10, P=.02) increased emotional support. However, asking questions depressed emotional support (beta=–.21, P<.001). In contrast, asking questions increased informational support (beta=.38, P<.001), whereas positive informational self-disclosure depressed it (beta=–.09, P=.003). Self-disclosure led to the perception of emotional needs, which elicited emotional support, whereas asking questions led to the perception of informational needs, which elicited informational support. Part 2 used machine-coded data to replicate these results. Part 3 analyzed the machine-coded data and showed that exposure to more emotional support predicted staying in the group longer 33% (hazard ratio=0.67, P<.001), whereas exposure to more informational support predicted leaving the group sooner (hazard ratio=1.05, P<.001). Conclusions Self-disclosure is effective in eliciting emotional support, whereas question asking is effective in eliciting informational support. Moreover, perceptions that people desire particular kinds of support influence the support they receive. Finally, the type of support people receive affects the likelihood of their staying in or leaving the group. These results demonstrate the utility of machine learning methods for investigating the dynamics of social support exchange in online support communities.

Identifying shared leadership in Wikipedia

In this paper, we introduce a method to measure shared leadership in Wikipedia as a step in developing a new model of online leadership. We show that editors with varying degrees of engagement and from peripheral as well as central roles all act like leaders, but that core and peripheral editors show different profiles of leadership behavior. Specifically, we developed machine learning models to automatically identify four types of leadership behaviors from 4 million messages sent between Wikipedia editors. We found strong evidence of shared leadership in Wikipedia, with editors in peripheral roles producing a large proportion of leadership behaviors.

Support matching and satisfaction in an online breast cancer support community

Research suggests that online health support benefits chronically ill users. Their satisfaction might be an indicator that they perceive group interactions as beneficial and a precursor to group commitment. We examined whether receiving emotional and informational support is satisfying in its own right, or whether satisfaction depends on matches between what users sought and what they received. Two studies collected judgments in a breast cancer support community of support users sought, support they received, and their expressed satisfaction. While receiving emotional or informational support in general positively predicted satisfaction, users expressed less satisfaction when they sought informational support but received emotional support. There was also a tendency for users to express more satisfaction when they sought and received informational support. On the other hand, users were equally satisfied with emotional and informational support after seeking emotional support. Implications for membership commitment and interventions in online support groups are discussed.

Modeling Self-Disclosure in Social Networking Sites

Social networking sites (SNSs) offer users a platform to build and maintain social connections. Understanding when people feel comfortable sharing information about themselves on SNSs is critical to a good user experience, because self-disclosure helps maintain friendships and increase relationship closeness. This observational research develops a machine learning model to measure self-disclosure in SNSs and uses it to understand the contexts where it is higher or lower. Features include emotional valence, social distance between the poster and people mentioned in the post, the language similarity between the post and the community and post topic. To validate the model and advance our understanding about online self-disclosure, we applied it to de-identified, aggregated status updates from Facebook users. Results show that women self-disclose more than men. People with a stronger desire to manage impressions self-disclose less. Network size is negatively associated with self-disclosure, while tie strength and network density are positively associated.

Web-based unsupervised learning for query formulation in question answering

Converting questions to effective queries is crucial to open-domain question answering systems. In this paper, we present a web-based unsupervised learning approach for transforming a given natural-language question to an effective query. The method involves querying a search engine for Web passages that contain the answer to the question, extracting patterns that characterize fine-grained classification for answers, and linking these patterns with n-grams in answer passages. Independent evaluation on a set of questions shows that the proposed approach outperforms a naive keyword-based approach in terms of mean reciprocal rank and human effort.

Investigating the effect of discussion forum interface affordances on patterns of conversational interactions

We investigate how the affordances provided by alternative interfaces for on-line discussion forums affect the structure of the discourse that unfolds. In order to investigate this impact, we compare the predictive power of time related and text similarity related features for identifying parent-child links between messages. The results from this work using this methodology suggest that interfaces that make parent-child relationships between messages explicit and do not constrain the choice of previous messages that users can reply to allow patterns of conversational behavior that violate the assumptions of traditional, tree-structured models of discourse where time related and similarity related features are highly predictive. An implication for future work is that because there is evidence that interface affordances affect the form of conversational contributions, techniques that process on-line communication data may need to be adapted for different communication interfaces.

Supporting the Guide on the SIDE

We present SIDE (the Summarization Integrated Development Environment), which is an infrastructure that facilitates the construction of reporting interfaces that support group learning facilitators in the task of getting a quick sense of the quality and effectiveness of a collaborative learning interaction. The SIDE framework offers flexibility in the specification of which conversational behavior to take note of as well as how noted behavior should be reported to instructors, making it a valuable research tool.