Items where author is affiliated with Shanghai Jiao Tong University

Automated text categorization is an important technique for many web applications, such as document indexing, document filtering, and cataloging web resources. Many different approaches have been proposed for the automated text categorization problem. Among them, centroid-based approaches have the advantages of short training time and testing time due to its computational efficiency. As a result, centroid-based classifiers have been widely used in many web applications. However, the accuracy of centroid-based classifiers is inferior to SVM, mainly because centroids found during construction are far from perfect locations. We design a fast Class-Feature-Centroid (CFC) classifier for multi-class, single-label text categorization. In CFC, a centroid is built from two important class distributions: inter-class term index and inner-class term index. CFC proposes a novel combination of these indices and employs a denormalized cosine measure to calculate the similarity score between a text vector and a centroid. Experiments on the Reuters-21578 corpus and 20-newsgroup email collection show that CFC consistently outperforms the state-of-the-art SVM classifiers on both micro-F1 and macro-F1 scores. Particularly, CFC is more effective and robust than SVM when data is sparse.

More and more structured information in the form of semantic data is nowadays available. It offers a wide range of new possibilities especially for semantic search and Web data integration. However, their effective exploitation still brings about a number of challenges, e.g. usability, scalability and uncertainty. In this paper, we present Dataplorer, a solution designed to address these challenges. We consider the usability through the use of hybrid queries and faceted search, while still preserving the scalability thanks to an extension of inverted index to support this type of query. Moreover, Dataplorer deals with uncertainty by means of a powerful ranking scheme to find relevant results. Our experimental results show that our proposed approach is promising and it makes us believe that it is possible to extend the current IR infrastructure to query and search the Web of data. Categories and Subject Descriptors: H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval General Terms: Algorithms, Performance, Experimentation Keywords: hybrid query, inverted index, ranking, faceted search sake of the others. The usability challenge is addressed by providing the user with hybrid query capabilities, leveraging the power of structured queries and the ease of use of keyword search. We also propose a faceted search functionality that allows users to progressively compose the structured part of their information need after having started with imprecise keywords. Scalability is one of the main challenges that hybrid queries are facing, due to the large amount of data. Inspired from the cross field of DB and IR integration, we make IR compatible with hybrid search through an extension of the inverted index, and thus able to scale as well as to handle structured information. To ensure that uncertainty does not remain as a problem to return relevant results, we provide a powerful ranking scheme that considers structures of both data and hybrid queries for score propagation and aggregation during results ranking. As an improvement of our previous work [3], we support faceted search with integrated ranking to tackle both usability and uncertainty issues while preserving efficiency.

Behavioral Targeting (BT) is a technique used by online advertisers to increase the effectiveness of their campaigns, and is playing an increasingly important role in the online advertising market. However, it is underexplored in academia how much BT can truly help online advertising in search engines. In this paper we provide an empirical study on the click-through log of advertisements collected from a commercial search engine. From the experiment results over a period of seven days, we draw three important conclusions: (1) Users who clicked the same ad will truly have similar behaviors on the Web; (2) Click-Through Rate (CTR) of an ad can be averagely improved as high as 670% by properly segmenting users for behavioral targeted advertising in a sponsored search; (3) Using short term user behaviors to represent users is more effective than using long term user behaviors for BT. We conducted statistical t-test which verified that all conclusions drawn in the paper are statistically significant. To the best of our knowledge, this work is the first empirical study for BT on the click-through log of real world ads.

Traditional Naive Bayes Classifier performs miserably on web-scale taxonomies. In this paper, we investigate the reasons behind such bad performance. We discover that the low performance are not completely caused by the intrinsic limitations of Naive Bayes, but mainly comes from two largely ignored problems: contradiction pair problem and discriminative evidence cancelation problem. We propose modifications that can alleviate the two problems while preserving the advantages of Naive Bayes. The experimental results show our modified Naive Bayes can significantly improve the performance on real web-scale taxonomies.