G. Alan Wang

Vehicle defect discovery from social media

A pressing need of vehicle quality management professionals is decision support for the vehicle defect discovery and classification process. In this paper, we employ text mining on a popular social medium used by vehicle enthusiasts: online discussion forums. We find that sentiment analysis, a conventional technique for consumer complaint detection, is insufficient for finding, categorizing, and prioritizing vehicle defects discussed in online forums, and we describe and evaluate a new process and decision support system for automotive defect identification and prioritization. Our findings provide managerial insights into how social media analytics can improve automotive quality management.

ExpertRank: A topic-aware expert finding algorithm for online knowledge communities

With increasing knowledge demands and limited availability of expertise and resources within organizations, professionals often rely on external sources when seeking knowledge. Online knowledge communities are Internet based virtual communities that specialize in knowledge seeking and sharing. They provide a virtual media environment where individuals with common interests seek and share knowledge across time and space. A large online community may have millions of participants who have accrued a large knowledge repository with millions of text documents. However, due to the low information quality of user-generated content, it is very challenging to develop an effective knowledge management system for facilitating knowledge seeking and sharing in online communities. Knowledge management literature suggests that effective knowledge management should make accessible not only written knowledge but also experts who are a source of information and can perform a given organizational or social function. Existing expert finding systems evaluate ones expertise based on either the contents of authored documents or ones social status within his or her knowledge community. However, very few studies consider both indicators collectively. In addition, very few studies focus on virtual communities where information quality is often poorer than that in organizational knowledge repositories. In this study we propose a novel expert finding algorithm, ExpertRank, that evaluates expertise based on both document-based relevance and ones authority in his or her knowledge community. We modify the PageRank algorithm to evaluate ones authority so that it reduces the effect of certain biasing communication behavior in online communities. We explore three different expert ranking strategies that combine document-based relevance and authority: linear combination, cascade ranking, and multiplication scaling. We evaluate ExpertRank using a popular online knowledge community. Experiments show that the proposed algorithm achieves the best performance when both document-based relevance and authority are considered.

What's buzzing in the blizzard of buzz? Automotive component isolation in social media postings

In the blizzard of social media postings, isolating what is important to a corporation is a huge challenge. In the consumer-related manufacturing industry, for instance, manufacturers and distributors are faced with an unrelenting, accumulating snow of millions of discussion forum postings. In this paper, we describe and evaluate text mining tools for categorizing this user-generated content and distilling valuable intelligence frozen in the mound of postings. Using the automotive industry as an example, we implement and tune the parameters of a text-mining model for component diagnostics from social media. Our model can automatically and accurately isolate the vehicle component that is the subject of a user discussion. The procedure described also rapidly identifies the most distinctive terms for each component category, which provides further marketing and competitive intelligence to manufacturers, distributors, service centers, and suppliers.

Identity matching using personal and social identity features

Identity verification is essential in our mission to identify potential terrorists and criminals. It is not a trivial task because terrorists reportedly assume multiple identities using either fraudulent or legitimate means. A national identification card and biometrics technologies have been proposed as solutions to the identity problem. However, several studies show their inability to tackle the complex problem. We aim to develop data mining alternatives that can match identities referring to the same individual. Existing identity matching techniques based on data mining primarily rely on personal identity features. In this research, we propose a new identity matching technique that considers both personal identity features and social identity features. We define two groups of social identity features including social activities and social relations. The proposed technique is built upon a probabilistic relational model that utilizes a relational database structure to extract social identity features. Experiments show that the social activity features significantly improve the matching performance while the social relation features effectively reduce false positive and false negative decisions.

Harnessing global expertise: A comparative study of expertise profiling methods for online communities

Building expertise profiles in global online communities is a critical step in leveraging the range of expertise available in the global knowledge economy. In this paper we introduce a three-stage framework that automatically generates expertise profiles of online community members. In the first two stages, document-topic relevance and user-document association are estimated for calculating users’ expertise levels on individual topics. We empirically compare two state-of-the-art information retrieval techniques, the vector space model and the language model, with a Latent Dirichlet Allocation (LDA) based model for computing document-topic relevance as well as the direct and indirect association models for computing user-document association. In the third stage we test whether a filtering strategy can improve the performance of expert profiling. Our experimental results using two real datasets provide useful insights on how to select the best models for profiling users’ expertise in online communities that can work across a range of global communities.

Multivariate measurement system analysis in multisite testing: An online technique using principal component analysis

Multisite testing improves manufacturing throughput and reduces costs by applying simultaneous testing to products with multiple measurement instruments in parallel. It is important to perform measurement system analysis (MSA) on a multisite testing system to assess its testing capability. Traditional MSA methods are designed to be either univariate or multivariate in a single-site system. They are not capable of analyzing a complex multisite testing system where there are multivariate measurements and multiple instruments in parallel. We propose an online multivariate MSA approach to detecting faulty test instruments in a multisite testing system. In order to pinpoint a faulty test instrument in a multisite testing system we compare the performance of each test instrument to the overall performance of all the parallel instruments in the system. A modified principal component analysis (PCA) method is proposed to transform multivariate measurement data with dependent variables into those with independent principal components. Assuming that all the instruments have the same measurement accuracy and precision we consider a faulty instrument as one whose principal component values are beyond the three sigma control limits of the principal component values of all instruments. We conduct an experiment to provide empirical evidence that the proposed approach is capable of identifying the faulty instruments in a multisite testing system. This approach can be implemented as an online monitoring technique so that production is not interrupted until a faulty instrument is identified.

An Analytical Framework for Understanding Knowledge-Sharing Processes in Online Q&A Communities

Online communities have become popular knowledge sources for both individuals and organizations. Computer-mediated communication research shows that communication patterns play an important role in the collaborative efforts of online knowledge-sharing activities. Existing research is mainly focused on either user egocentric positions in communication networks or communication patterns at the community level. Very few studies examine thread-level communication and process patterns and their impacts on the effectiveness of knowledge sharing. In this study, we fill this research gap by proposing an innovative analytical framework for understanding thread-level knowledge sharing in online Q&A communities based on dialogue act theory, network analysis, and process mining. More specifically, we assign a dialogue act tag for each post in a discussion thread to capture its conversation purpose and then apply graph and process mining algorithms to examine knowledge-sharing processes. Our results, which are based on a real support forum dataset, show that the proposed analytical framework is effective in identifying important communication, conversation, and process patterns that lead to helpful knowledge sharing in online Q&A communities.

CUSUM Control Charts for Multivariate Poisson Distribution

A cumulative sum control chart for multivariate Poisson distribution (MP-CUSUM) is proposed. The MP-CUSUM chart is constructed based on log-likelihood ratios with in-control parameters, Θ0, and shifts to be detected quickly, Θ1. The average run length (ARL) values are obtained using a Markov Chain-based method. Numerical experiments show that the MP-CUSUM chart is effective in detecting parameter shifts in terms of ARL. The MP-CUSUM chart with smaller Θ1 is more sensitive than that with greater Θ1 to smaller shifts, but more insensitive to greater shifts. A comparison shows that the proposed MP-CUSUM chart outperforms an existing MP chart.

Modified multivariate process capability index using principal component analysis

The existing research of process capability indices of multiple quality characteristics mainly focuses on nonconforming of process output, the concept development of univariate process capability indices, quality loss function and various comprehensive evaluation methods. The multivariate complexity increases the computation difficulty of multivariate process capability indices(MPCI), which makes them hard to be used in practice. In this paper, a new PCA-based MPCI approach is proposed to assess the production capability of the processes that involve multiple product quality characteristics. This approach first transforms the original quality variables into standardized normal variables. MPCI measures are then provided based on the Taam index. Moreover, the statistical properties of these MPCIs, such as confidence intervals and lower confidence bound, are given to let the practitioners understand the capability indices as random variables instead of deterministic variables. A real manufacturing data set and a synthetic data set are used to demonstrate the effectiveness of the proposed method. An implementation procedure is also provided for quality engineers to apply our MPCI approach in their manufacturing processes. The case studies demonstrate the effectiveness and feasibility of this new kind of MPCI, which is easier to be used in production practice. The proposed research provides a novel approach of MPCI calculation.

A hierarchical Naïve Bayes model for approximate identity matching

Organizations often manage identity information for their customers, vendors, and employees. Identity management is critical to various organizational practices ranging from customer relationship management to crime investigation. The task of searching for a specific identity is difficult because disparate identity information may exist due to the issues related to unintentional errors and intentional deception. In this paper we propose a hierarchical Naive Bayes model that improves existing identity matching techniques in terms of searching effectiveness. Experiments show that our proposed model performs significantly better than the exact-match based matching technique. With 50% training instances labeled, the proposed semi-supervised learning achieves a performance comparable to the fully supervised record comparison algorithm. The semi-supervised learning greatly reduces the efforts of manually labeling training instances without significant performance degradation.