Richong Zhang

An information gain-based approach for recommending useful product reviews

Recently, many e-commerce Web sites, such as Amazon.com, provide platforms for users to review products and share their opinions, in order to help consumers make their best purchase decisions. However, the quality and the level of helpfulness of different product reviews are not disclosed to consumers unless they carefully analyze an immense number of lengthy reviews. Considering the large amount of available online product reviews, this is an impossible task for any consumer. Therefore, it is of vital importance to develop recommender systems that can evaluate online product reviews effectively to recommend the most useful ones to consumers. This paper proposes an information gain-based model to predict the helpfulness of online product reviews, with the aim of suggesting the most suitable products and vendors to consumers. Reviews are analyzed and ranked by our scoring model and reviews that help consumers better than others will be found. In addition, we also compare our model with several machine learning algorithms. Our experimental results show that our approach is effective in ranking and classifying online product reviews.

A Probabilistic Approach for Web Service Discovery

Web service discovery is a vital problem in service computing with the increasing number of services. Existing service discovery approaches merely focus on WSDL-based keyword search, semantic matching based on domain knowledge or ontologies, or QoS-based recommendations. The keyword search omits the underlying correlations and semantic knowledge or QoS information is not always available. In this paper, we propose a probabilistic service discovery approach to help web service users to retrieve related services and to improve the search performance. Specifically, we apply a probabilistic model to characterize the latten topics between services and queries, and then propose a matching method based on the topic relevance. Experiments on services from a real service repository confirm the feasibility and efficiency of this proposed method.

A Novel Approach for API Recommendation in Mashup Development

Mashing up Web services and RESTful APIs is a novel programming approach to develop new applications. As the number of available resources is increasing rapidly, to discover potential services or APIs is getting difficult. Therefore, it is vital to relieve mashup developers of the burden of service discovery. In this paper, we propose a probabilistic model to assist mashup creators by recommending a list of APIs that may be used to compose a required mashup given descriptions of the mashup. Specifically, a relational topic model is exploited to characterize the relationship among mashups, APIs and their links. In addition, we incorporate the popularity of APIs to the model and make predictions on the links between mashups and APIs. Moreover, the statistical analysis on a public mashup platform shows the current status of mashup development and the applicability of this study. Experiments on a large service data set confirm the effectiveness of this proposed approach.

Opinion helpfulness prediction in the presence of words of few mouths

This paper identifies a widely existing phenomenon in social media content, which we call the “words of few mouths” phenomenon. This phenomenon challenges the development of recommender systems based on users’ online opinions by presenting additional sources of uncertainty. In the context of predicting the “helpfulness” of a review document based on users’ online votes on other reviews (where a user’s vote on a review is either HELPFUL or UNHELPFUL), the “words of few mouths” phenomenon corresponds to the case where a large fraction of the reviews are each voted only by very few users. Focusing on the “review helpfulness prediction” problem, we illustrate the challenges associated with the “words of few mouths” phenomenon in the training of a review helpfulness predictor. We advocate probabilistic approaches for recommender system development in the presence of “words of few mouths”. More concretely, we propose a probabilistic metric as the training target for conventional machine learning based predictors. Our empirical study using Support Vector Regression (SVR) augmented with the proposed probability metric demonstrates advantages of incorporating probabilistic methods in the training of the predictors. In addition to this “partially probabilistic” approach, we also develop a logistic regression based probabilistic model and correspondingly a learning algorithm for review helpfulness prediction. We demonstrate experimentally the superior performance of the logistic regression method over SVR, the prior art in review helpfulness prediction.

Helping E-Commerce Consumers Make Good Purchase Decisions: A User Reviews-Based Approach

Online product reviews provided by the consumers, who have previously purchased and used some particular products, form a rich source of information for other consumers who would like to study about these products in order to make their purchase decisions. Realizing this great need of consumers, several e-commerce web sites such as Amazon.com offer facilities for consumers to review products and exchange their purchase opinions. Unfortunately, reading through the massive amounts of product reviews available online from many e-communities, forums and newsgroups is not only a tedious task but also an impossible one. Indeed, nowadays consumers need an effective and reliable method to search through those huge sources of information and sort out the most appropriate and helpful product reviews. This paper proposes a model to discover the helpfulness of online product reviews. Product reviews can be analyzed and ranked by our scoring system and those reviews that may help consumers better than others will be found. In addition, we compare our model with a number of machine learning techniques. Our experimental results confirm that our approach is effective in ranking and classifying online product reviews.

Bursty event detection from microblog: a distributed and incremental approach

As a new form of social media, microblogs (e.g., Twitter and Weibo) are playing an important role in peoples daily life. With the rise in popularity and size of microblogs, there is a need for distributed approaches that can detect bursty event with low latency from the short‐text data stream. In this paper, we propose a distributed and incremental temporal topic model for microblogs called Bursty Event dEtection (BEE+). BEE+ is able to detect bursty events from short‐text dataset and model the temporal information. And BEE+ processes the post‐stream incrementally to track the topic drifting of events over time. Therefore, the latent semantic indices are preserved from one time period to the next. In order to achieve real‐time processing, we design a distributed execution framework based on Spark engine. To verify its ability to detect bursty event, we conduct experiments on a Weibo dataset of 6,360,125 posts. The results show that BEE+ can outperform the baselines for detecting the meaningful bursty events and track the topic drifting. Copyright

Online Bursty Event Detection from Microblog

Microblogs (e.g., Twitter and Weibo) have become a large social media platform for users to share contents, their interests and events with friends. A surge of the number of event related posts always reflects that some peoples concern real-life events happened. In this paper, we propose an incremental temporal topic model for microblogs namely BEE (Bursty Event Detection) to detect these bursty events. BEE supports to detect these bursty events from short text datasets through modeling the temporal information of events. And BEE employs processing the post streaming incrementally to track the topic of events drifting over time. Therefore, the latent semantic indices are preserved from one time period to the next. After BEE detects the event-driven posts and related events, the bur sty detection module can identify the bursty patterns for each event and rank the events using the bursty patterns. Our experiments on a large Weibo dataset show that our algorithm can outperform the baselines for detecting the meaningful bur sty events. Subsequently, we also show some case studies that indicate the effectiveness of the temporal factor for bursty event detection and how well BEE can track the topic drifting of events.

An Entropy-Based Model for Discovering the Usefulness of Online Product Reviews

E-commerce Web sites, such as Amazon.com, provide platforms for consumers to review products and share their opinions. However, it is impossible for consumers to read throughout the huge amount of available reviews. In addition, the quality and helpfulness of reviews are unavailable unless consumers have to read through them.This paper proposes an entropy-based model to predict the helpfulness of reviews. Reviews can be ranked by our entropy-based scoring model and reviews that may help consumers better than others will be found. We also compare our model with several machine learning algorithms. Our experimental results show that our approach is effective in ranking and classifying online reviews. With the predicted helpfulness of reviews, consumers can make purchase decisions more easily.

Ring: Real-Time Emerging Anomaly Monitoring System over Text Streams

Microblog platforms have been extremely popular in the big data era due to its real-time diffusion of information. Its important to know what anomalous events are trending on the social network and be able to monitor their evolution and find related anomalies. In this paper we demonstrate <sc>Ring</sc>, a <underline>r</underline>eal-t<underline>i</underline>me emerging a<underline>n</underline>omaly monitorin<underline>g</underline> system over microblog text streams. <sc>Ring</sc> integrates our efforts on both emerging anomaly monitoring research and system research. From the anomaly monitoring perspective, <sc>Ring</sc> proposes a graph analytic approach such that (1) <sc>Ring</sc> is able to detect emerging anomalies at an earlier stage compared to the existing methods, (2) <sc>Ring</sc> is among the first to discover emerging anomalies correlations in a streaming fashion, (3) <sc>Ring</sc> is able to monitor anomaly evolutions in real-time at different time scales from minutes to months. From the system research perspective, <sc>Ring</sc> (1) optimizes time-ranged keyword query performance of a full-text search engine to improve the efficiency of monitoring anomaly evolution, (2) improves the dynamic graph processing performance of Spark and implements our graph stream model on it, As a result, <sc>Ring</sc> is able to process big data to the entire Weibo or Twitter text stream with linear horizontal scalability. The system clearly presents its advantages over existing systems and methods from both the event monitoring perspective and the system perspective for the emerging event monitoring task.

Effective Result Inference for Context-Sensitive Tasks in Crowdsourcing

Effective result inference is an important crowdsourcing topic as workers may return incorrect results. Existing inference methods assign each task to multiple workers and aggregate the results from these workers to infer the final answer. However, these methods are rather ineffective for context-sensitive tasks (\(\mathtt{CSTs}\)), e.g., handwriting recognition, due to the following reasons. First, each \(\mathtt{CST}\) is rather hard and workers usually cannot correctly answer a whole \(\mathtt{CST}\). Thus a task-level inference strategy cannot achieve high-quality results. Second, a \(\mathtt{CST}\) should not be divided into multiple subtasks because the subtasks are correlated with each other under certain contexts. So a subtask-level inference strategy cannot achieve high-quality results as it neglects the correlation between subtasks. Thus it calls for an effective result inference method for \(\mathtt{CSTs}\). To address this challenge, this paper proposes a smart assembly model (\(\mathtt{SAM}\)), which can assemble workers’ complementary answers in the granularity of subtasks without losing the context information. Furthermore, we devise an iterative decision model based on the partially observable Markov decision process, which can decide whether we need to ask more workers to get better results. Experimental results show that our method outperforms state-of-the-art approaches.