Online Knowledge Community Mining and Modeling for Effective Knowledge Management
|dc.description.abstract|| More and more in recent years, activities that people once did in the real world they now do in virtual space. In particular, online communities have become popular and efficient media for people all over the world to seek and share knowledge in domains that interest them. Such communities are called online knowledge communities (OKCs). Large-scale OKCs may comprise thousands of community members and archive many more online messages. As a result, problems such as how to identify and manage the knowledge collected and how to understand people\'s knowledge-sharing behaviors have become major challenges for leveraging online knowledge to sustain community growth.|
In this dissertation I examine three important factors of managing knowledge in OKCs. First, I focus on how to build successful profiles for community members that describe their domain expertise. These expertise profiles are potentially important for directing questions to the right people and, thus, can improve the community\'s overall efficiency and efficacy. To address this issue, I present a comparative study of models of expertise profiling in online communities and identify the model combination that delivers the best results.
Next, I investigate how to automatically assess the information helpfulness of user postings. Due to the voluntary nature of online participation, there is no guarantee that all user-generated content (UGC) will be helpful. It is also difficult, given the sheer amount of online postings, for knowledge seekers to find information quickly that satisfies their informational needs. Therefore, I propose a theory-driven text classification framework based on the knowledge adoption model (KAM) for predicting the helpfulness of UGC in OKCs. I test the effectiveness of this framework at both the thread level and the post level of online messages.
Any given OKC generally has a huge number of individuals participating in online discussions, but exactly what, where, when and how they seek and share knowledge are still not fully understood or documented. In the last part of the dissertation, I describe a multi-level study of the knowledge-sharing behaviors of users in OKCs. Both exploratory data analysis and network analysis are applied to thread, forum and community levels of online data. I present a number of interesting findings on social dynamics in knowledge sharing and diffusion. These findings potentially have important implications for both the theory and practice of online community knowledge management.
|dc.rights||This Item is protected by copyright and/or related rights. Some uses of this Item may be deemed fair and permitted by law even without permission from the rights holder(s), or the rights holder(s) may have licensed the work for use under certain conditions. For other uses you need to obtain permission from the rights holder(s).||en_US|
|dc.subject||Knowledge Helpfulness Prediction||en_US|
|dc.subject||Knowledge Sharing & Diffusion||en_US|
|dc.title||Online Knowledge Community Mining and Modeling for Effective Knowledge Management||en_US|
|thesis.degree.grantor||Virginia Polytechnic Institute and State University||en_US|
|thesis.degree.discipline||Computer Science and Applications||en_US|
|dc.contributor.committeechair||Fan, Weiguo Patrick||en_US|
|dc.contributor.committeemember||Fox, Edward A.||en_US|
Files in this item
This item appears in the following Collection(s)
Doctoral Dissertations