Daling Wang

Extracting common emotions from blogs based on fine-grained sentiment clustering

Recently, blogs have emerged as the major platform for people to express their feelings and sentiments in the age of Web 2.0. The common emotions, which reflect people’s collective and overall sentiments, are becoming the major concern for governments, business companies and individual users. Different from previous literatures on sentiment classification and summarization, the major issue of common emotion extraction is to find out people’s collective sentiments and their corresponding distributions on the Web. Most existing blog clustering methods take into account keywords, stories or timelines but neglect the embedded sentiments, which are considered very important features of blogs. In this paper, a novel method based on Probabilistic Latent Semantic Analysis (PLSA) is presented to model the hidden sentiment factors and an emotion-oriented clustering approach is proposed to find common emotions according to the fine-grained sentiment similarity between blogs. Extensive experiments are conducted on real-world datasets consisting of different topics. The results show that our approach can partition blogs into sentiment coherent clusters and the extracted common emotion words afford good navigation guidelines for embedded sentiments in each cluster.

An Improved Spectral Clustering Algorithm for Community Discovery

For discovering communities in social network, an improved spectral clustering method is presented in this paper. To make full use of the network feature, the core members are used in this method for mining communities. This goal has been achieved through the Page Rank method, which is common in directed graphs, for the reason that an undirected graph can be treated as the special case of the corresponding directed one. Following that, they can be used for initialization in the spectral clustering to avoid the sensitivity to the initial centroids. Applied to four datasets, the improved method turns out to be better than the traditional spectral clustering methods, whether in time or in accuracy aspect.

CD-Trees: An Efficient Index Structure for Outlier Detection

Outlier detection is to find objects that do not comply with the general behavior of the data. Partition is a kind of method of dividing data space into a set of non-overlapping rectangular cells. There exists very large data skew in real-life datasets so that partition will produce many empty cells. The cell-based algorithms for outlier detection don’t get enough attention to the existence of many empty cells, which affects the efficiency of algorithms. In this paper, we propose the concept of Skew of Data (SOD) to measure the degree of data skew, and which approximates the percentage of empty cells under a partition of a dataset. An efficient index structure called CD-Tree and the related algorithms are designed. This paper applies the CD-Tree to detect outliers. Compared with cell-based algorithms on real-life datasets, the speed of CD-Tree-based algorithm increases 4 times at least and that the number of dimensions processed also increases obviously.

A word-emoticon mutual reinforcement ranking model for building sentiment lexicon from massive collection of microblogs

Recently, more and more researchers have focused on the problem of analyzing people’s sentiments and opinions in social media. The sentiment lexicon plays a crucial role in most sentiment analysis applications. However, the existing thesaurus based lexicon building methods suffer from the coverage problems when faced with the new words and new meanings in social media. On the other hand, the previous learning based methods usually need intensive expert efforts for annotating training datasets or designing extraction patterns. In this paper, we observe that the graphical emoticons are good natural sentiment labels for the corresponding microblog posts and a word-emoticon mutual reinforcement ranking model is proposed to learn the sentiment lexicon from the massive collection of microblog data. We integrate the emoticons and candidate sentiment words in the microblogs to construct a two-layer graph, on which a random walk is run for extracting the top ranked words as a sentiment lexicon. Extensive experiments were conducted on a benchmark dataset with various topics. The results validate the effectiveness of the proposed methods in building sentiment lexicon from microblog data.

Using Page Classification and Association Rule Mining for Personalized Recommendation in Distance Learning

With the rapid development of Internet, distance learning applications over Internet become more and more popular. This paper introduces a personalized learning system for web-based distance learning and focus on the web usage mining techniques aimed at personalized recommendation service. First, this paper presents a web page classification method, which uses attribute-oriented induction method according to related domain knowledge shown by a concept hierarchy tree. Second, the paper presents an algorithm of mining association rules with one-support using Freq-Set-Tree. Third, based on their current access patterns, page classes at the home site, page integration from other sites, and the rules discovered in mining, recommendation pages are made and presented for the students.

A novel approach for clustering sentiments in Chinese blogs based on graph similarity

Blog clustering is an important approach for online public opinion analysis. The traditional clustering methods, usually group blogs by keywords, stories and timeline, which usually ignore opinions and emotions expressed in the blog articles. In this paper, an integrated graph-based model for clustering Chinese blogs by embedded sentiments is proposed. A novel graph-based representation and the corresponding clustering algorithm are applied on the Chinese blog search results. The proposed model SoB-graph considers not only sentiment words but also structural information in blogs. Experimental results show that comparing with the traditional graph-based document representation model and vector space document representation model, the proposed SoB-graph model has achieved better performance in clustering sentiments in Chinese blog documents.

Build Emotion Lexicon from Microblogs by Combining Effects of Seed Words and Emoticons in a Heterogeneous Graph

As an indispensable resource for emotion analysis, emotion lexicons have attracted increasing attention in recent years. Most existing methods focus on capturing the single emotional effect of words rather than the emotion distributions which are helpful to model multiple complex emotions in a subjective text. Meanwhile, automatic lexicon building methods are overly dependent on seed words but neglect the effect of emoticons which are natural graphical labels of fine-grained emotion. In this paper, we propose a novel emotion lexicon building framework that leverages both seed words and emoticons simultaneously to capture emotion distributions of candidate words more accurately. Our method overcomes the weakness of existing methods by combining the effects of both seed words and emoticons in a unified three-layer heterogeneous graph, in which a multi-label random walk (MLRW) algorithm is performed to strengthen the emotion distribution estimation. Experimental results on real-world data reveal that our constructed emotion lexicon achieves promising results for emotion classification compared to the state-of-the-art lexicons.

A Novel Approach Based on Multi-View Content Analysis and Semi-Supervised Enrichment for Movie Recommendation

Although many existing movie recommender systems have investigated recommendation based on information such as clicks and tags, much less efforts have been made to explore the multimedia content of movies, which has potential information for the elicitation of the user’s visual and musical preferences. In this paper, we explore the content from three media types (image, text, audio) and propose a novel multi-view semi-supervised movie recommendation method, which represents each media type as a view space for movies. The three views of movies are integrated to predict the rating values under the multi-view framework. Furthermore, our method considers the casual users who rate limited movies. The algorithm enriches the user profile with a semi-supervised way when there are only few rating histories. Experiments indicate that the multimedia content analysis reveals the user’s profile in a more comprehensive way. Different media types can be a complement to each other for movie recommendation. And the experimental results validate that our semi-supervised method can effectively enrich the user profile for recommendation with limited rating history.

A web-based transformation system for massive scientific data

In the domain of science research, a mass of data obtained and generated by instruments are in the form of text. How to make the best use of these data has become one of the issues for both nature science researchers and computer professions. Many of these data contain their logic structure inside, but they are different from the self-describing semi-structured data, for these data are separate from the schema. Because of the great increase of the data amount, the traditional way of studying on these data can not meet the needs of high performance and flexible access. Relational DBMS is a good technique for organizing and managing data. In this paper, a mapping model—STRIPE—between scientific text and relational database is proposed. Using STRIPE, we design and implement a Web-based massive scientific data transformation system, which gives a good solution to the problem of the massive scientific data management, query and exchange. The evaluation to the system shows that it can greatly improve the efficiency of scientific data transformation, and offer scientists a novel platform for studying the data.

A Role and Context Based Access Control Model with UML

As the wide uses of access control model in systems, a more agile access control model is required to solve complicated modeling, user authorizing and verifying problem. In this paper, an access control model based on the concepts of role, attribute and context, named C-RBAC, is proposed. This model is based on and further improved role-based access control (RBAC). The proposed model adds system conditions in access control, distinguishes users that belong to one role by user attributes, provides an agile and dynamic role model by adopting the concept of conditional role, and designs a more flexible access authorization mechanism to reinforce role model of RBAC. The implementation and the UML-modeling approaches of proposed model are also explained in this paper. Theoretical analysis and experiments prove that the new access control model is more effective by comparing with traditional RBAC model.