School of Computing and AI

In this paper, we propose a novel approach to automatically detect "hot" or important topics of discussion in the blogosphere. The proposed approach is based on analyzing the activity of influential bloggers to determine specific points in time when there is a convergence amongst the influential bloggers in terms of their topic of discussion. The tool BlogTrackers, is used to identify influential bloggers and the Normalized Google Distance is used to define the similarity amongst the topics of discussion of influential bloggers. The key advantage of the proposed approach is its ability to automatically detect events which are important in the blogger community.

A topic taxonomy is an effective representation that describes salient features of virtual groups or online communities. A topic taxonomy consists of topic nodes. Each internal node is defined by its vertical path (i.e., ancestor and child nodes) and its horizonal list of attributes (or terms). In a text-dominant environment, a topic taxonomy can be used to flexibly describe a group's interests with varying granularity. However, the stagnant nature of a taxonomy may fail to timely capture the dynamic change of a group's interest. This article addresses the problem of how to adapt a topic taxonomy to the accumulated data that reflects the change of a group's interest to achieve dynamic group profiling. We first discuss the issues related to topic taxonomy. We next formulate taxonomy adaptation as an optimization problem to find the taxonomy that best fits the data. We then present a viable algorithm that can efficiently accomplish taxonomy adaptation. We conduct extensive...

Abstract: Due to the digitization of data and advances in technology, it has become extremely easy to obtain and store large quantities of data, particularly Multimedia data. Fields ranging from Commercial to Military need to analyze these data in an efficient and fast manner. Presently, tools for mining images are few and require human intervention. Feature selection and extraction is the pre-processing step of Image Mining. Obviously this is a critical step in the entire scenario of Image Mining. Our approach to mine from Images–to ...

The study of collective behavior is to understand how individuals behave in a social network environment. Oceans of data generated by social media like Facebook, Twitter, Flickr and YouTube present opportunities and challenges to studying collective behavior in a large scale. In this work, we aim to learn to predict collective behavior in social media. In particular, given information about some individuals, how can we infer the behavior of unobserved individuals in the same network? A social-dimension based approach is adopted to address the heterogeneity of connections presented in social media. However, the networks in social media are normally of colossal size, involving hundreds of thousands or even millions of actors. The scale of networks entails scalable learning of models for collective behavior prediction. To address the scalability issue, we propose an edge-centric clustering scheme to extract sparse social dimensions. With sparse social dimensions, the socialdimension based approach can efficiently handle networks of millions of actors while demonstrating comparable prediction performance as other non-scalable methods.

A multi-mode network consists of heterogeneous types of actors with various interactions occurring between them. Identifying communities in a multi-mode network can help understand the structural properties of the network, address the data shortage and unbalanced problems, and assist tasks like targeted marketing and finding influential actors within or between groups. In general, a network and its group structure often evolve unevenly. In a dynamic multimode network, both group membership and interactions can evolve, posing a challenging problem of identifying these evolving communities. In this work, we try to address this problem by employing the temporal information to analyze a multi-mode network. A temporally-regularized framework and its convergence property are carefully studied. We show that the algorithm can be interpreted as an iterative latent semantic analysis process, which allows for extensions to handle networks with actor attributes and within-mode interactions. Experiments on both synthetic data and realworld networks demonstrate the efficacy of our approach and suggest its generality in capturing evolving groups in networks with heterogeneous entities and complex relationships.

Researchers spend considerable time searching for relevant papers on the topic in which they are currently interested. Often, despite having similar interests, researchers in the same laboratory do not find it convenient to share results of bibliographic searches and thus conduct independent time-consuming searches. Research paper recommender systems can help the researcher avoid such time-consuming searches by allowing each researcher to automatically take advantage of previous searches performed by others in the lab. Existing recommender systems were developed for commercial domains to assist users by focusing toward products of their interests. Unlike those domains, the research paper domain has relatively few users when compared with the significantly larger number of research papers. In this paper, we present a novel system to recommend relevant research papers to a user based on the user’s recent querying and browsing habits. The core of the system is a scalable subspace clust...

Blogosphere is expanding in an unprecedented speed. A better understanding of the blogosphere can greatly facilitate the development of the Social Web to serve the needs of users, service providers and advertisers. One important task in this process is clustering blog sites. Clustering blog sites presents new challenges. We propose to tap into collective wisdom in clustering blog sites, present statistical and visual results, report findings, and suggest future work extending to many real-world applications.

The problem of inferring a user's intentions in Machine–Human Interaction has been the key research issue for providing personalized experiences and services. In this paper, we propose novel approaches on modeling and inferring user's actions in a computer. Two linguistic features – keyword and concept features – are extracted from the semantic context for intention modeling. Concept features are the

The World Wide Web has now become a humongous archive of various contents. The inordinate amount of information found on the web presents a challenge to deliver right information to the right users. On one hand, the abundant information is freely accessible to all web denizens; on the other hand, much of such information may be irrelevant or even deleterious to some users. For example, some control and filtering mechanisms are desired to prevent inappropriate or offensive materials such as pornographic websites from reaching children. Ways of accessing websites are termed as Access Scenarios . An Access Scenario can include using search engines (e.g., image search that has very little textual content), URL redirection to some websites, or directly typing (porn) website URLs. In this paper we propose a framework to analyze a website from several different aspects or information sources, and generate a classification model aiming to accurately classify such content irrespective of acc...

Weblogs, or Blogs, have facilitated people to express their thoughts, voice their opinions, and share their experiences and ideas. Individuals experience a sense of community, a feeling of belonging, a bonding that members matter to one another and their niche needs will be met through online interactions. Its open standards and low barrier to publication have transformed information consumers to producers. This has created a plethora of open-source intelligence, or "collective wisdom" that acts as the storehouse of over-whelming amounts of knowledge about the members, their environment and the symbiosis between them. Nonetheless, vast amounts of this knowledge still remain to be discovered and exploited in its suitable way. In this paper, we introduce various state-of-the-art research issues, review some key elements of research such as tools and methodologies in Blogosphere, and present a case study of identifying the influential bloggers in a community to exemplify the ...

Blogging becomes a popular way for a Web user to publish information on the Web. Bloggers write blog posts, share their likes and dislikes, voice their opinions, provide suggestions, report news, and form groups in Blogosphere. Bloggers form their virtual communities of similar interests. Activities happened in Blogosphere affect the external world. One way to understand the development on Blogosphere is to find influential blog sites. There are many non-influential blog sites which form the "the long tail". Regardless of a blog site being influential or not, there are influential bloggers. Inspired by the high impact of the influentials in a physical community, we study a novel problem of identifying influential bloggers at a blog site. Active bloggers are not necessarily influential. Influential bloggers can impact fellow bloggers in various ways. In this paper, we discuss the challenges of identifying influential bloggers, investigate what constitutes influential bloggers, present a preliminary model attempting to quantify an influential blogger, and pave the way for building a robust model that allows for finding various types of the influentials. To illustrate these issues, we conduct experiments with data from a real-world blog site, evaluate multi-facets of the problem of identifying influential bloggers, and discuss unique challenges. We conclude with interesting findings and future work.

Researchers from the same lab often spend a considerable amount of time searching for published articles relevant to their current project. Despite having similar interests, they conduct independent, time consuming searches. While they may share the results afterwards, they are unable to leverage previous search results during the search process. We propose a research paper recommender system that avoids such time consuming searches by augmenting existing search engines with recommendations based on previous searches performed by others in the lab. Most existing recommender systems were developed for commercial domains with millions of users. The research paper domain has relatively few users compared to the large number of online research papers. The two major challenges with this type of data are the large number of dimensions and the sparseness of the data. The novel contribution of the paper is a scalable subspace clustering algorithm (SCuBA 1) that tackles these problems. Both synthetic and benchmark datasets are used to evaluate the clustering algorithm and to demonstrate that it performs better than the traditional collaborative filtering approaches when recommending research papers.

Email usage is pervasive among people from different backgrounds, and email corpus can be an important data source to study intricate social structures. Social status and role analysis on a personal email network can help reveal hidden information. The availability of Sarah Palin's email corpus presents a great opportunity to study social statuses and social roles in an email network. However, the email corpus does not readily lend itself to social network analysis due to problems such as noisy email data, scale in size, and temporal constraints. In this paper, we report an initial investigation of social status and role analysis on Sarah Palin's email corpus. In particular, we conduct a preliminary study on Palin's social statuses and roles. To the best of our knowledge, this work is the first exploration of Sarah Palin's email corpus recently released by the state of Alaska.

Universality, the property of the Web that makes it the largest data and information source in the world, is also the property behind the lack of a uniform organization scheme that would allow easy access to data and information. A semantic web, wherein different applications and Web sites can exchange information and hence exploit Web data and information to their full potential, requires the information about Web resources to be represented in a detailed and structured manner. Resource Description Framework (RDF), an effort in this direction supported by the World Wide Web Consortium, provides a means for the description of metadata which is a necessity for the next generation of interoperable Web applications. The success of RDF and the semantic web will depend on (1) the development of applications that prove the applicability of the concept, (2) the availability of application interfaces which enable the development of such applications, and (3) databases and inference systems ...

In this work, we examine familiar strangers on Blogosphere and issues of finding them. In our daily life, familiar strangers, as coined by Stanley Milgram, do not know each other, but frequently exhibit some common patterns. Blogosphere is a part of the Web where bloggers post in individual or community blog sites. The nature of the Web is a scale-free network, which determines that a power law distribution applies to bloggers. That is, the majority bloggers are only connected with a small number of fellow bloggers, and these blogging groups are largely disconnected from each other. Familiar strangers on Blogosphere are not directly connected, but share some patterns in their blogging activities. We present a new problem: Aggregating familiar strangers on Blogosphere that allows for better personalized services, targeted marketing, exploration of new business opportunities, and predictive modeling and marketing. Finding familiar strangers on Blogosphere presents a challenge resulting from their disconnectedness. We look at typical blogs and understand the status quo, while seeking innovative ways to improve business intelligence. We define the problem of searching for familiar strangers on Blogosphere, elucidate the significance of doing so, study the challenges of finding them, and present and discuss some potential approaches.

The increasing popularity of social media is shortening the distance between people. Social activities, e.g., tagging in Flickr, bookmarking in Delicious, twittering in Twitter, etc. are reshaping people's social life and redefining their social roles. People with shared interests tend to form their groups in social media, and users within the same community likely exhibit similar social behavior (e.g., going for the same movies, having similar political viewpoints), which in turn reinforces the community structure. The multiple interactions in social activities entail that the community structures are often overlapping, i.e., one person is involved in several communities. We propose a novel co-clustering framework, which takes advantage of networking information between users and tags in social media, to discover these overlapping communities. In our method, users are connected via tags and tags are connected to users. This explicit representation of users and tags is useful for understanding group evolution by looking at who is interested in what. The efficacy of our method is supported by empirical evaluation in both synthetic and online social networking data.

As the competition of Web search market increases, there is a high demand for personalized Web search to conduct retrieval incorporating Web users' information needs. This paper focuses on utilizing clickthrough data to improve Web search. Since millions of searches are conducted everyday, a search engine accumulates a large volume of clickthrough data, which records who submits queries and which pages he/she clicks on. The clickthrough data is highly sparse and contains different types of objects (user, query and Web page), and the relationships among these objects are also very complicated. By performing analysis on these data, we attempt to discover Web users' interests and the patterns that users locate information. In this paper, a novel approach CubeSVD is proposed to improve Web search. The clickthrough data is represented by a 3-order tensor, on which we perform 3-mode analysis using the higher-order singular value decomposition technique to automatically capture the latent factors that govern the relations among these multi-type objects: users, queries and Web pages. A tensor reconstructed based on the CubeSVD analysis reflects both the observed interactions among these objects and the implicit associations among them. Therefore, Web search activities can be carried out based on CubeSVD analysis. Experimental evaluations using a real-world data set collected from an MSN search engine show that CubeSVD achieves encouraging search results in comparison with some standard methods.