Browsing by Author "Pathak, Nishith"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Analyzing information flow in social networks for knowledge discovery(2013-02) Pathak, NishithIn the last few years the online world has seen a surge in users’ social behavior. No longer is the image of a lone user surfing the web relevant anymore and with social sites such as Facebook, Twitter, etc. online users can now actively interact with other users. It is now quite common for web businesses to offer support for friends lists, forums, private message systems, community maintenance tools etc. As as result, not only are users finding more social satisfication online, but the businesses themselves are now able to interact with and monitor the communities around them. Consequently, large amounts of data are being collected from such “social systems”, which capture users’ participation in the community. The data can include user-user interactions as well as their activities with time stamps. The data is also unique in that it captures complex social phenomenon in a much more comprehensive manner and at a much more finer granularity, than any other traditional source of communication data. This presents rich opportunities for the development of knowledge discovery algorithms which will find immense value in revealing trends, latent structures or interesting behaviors in these social systems. In any social system, communication exposes people to information, opinions as well as behavior of other users. According to a well studied phenomenon in social science, summarized in the theory of contagion, users in such networks tend to develop beliefs, attitudes and assumptions that are similar to those of others around them. By “word-of-mouth” rumors, ideas, opinions, information, etc. can propagate to different regions in the network. The research presented in this thesis explores the analysis of such information flow in social networks from a variety of perspectives, including the network topology, actors’ interests, actors’ cognition and actors’ influence. It is shown that the proposed analyses techniques can discover valuable knowledge regarding community structure, user interests and sentiments, as well as prominent users in the community. Such knowledge is of immense value to online business owners, as it allows them to monitor and identify factors for improving the overall experience of their users.Item Inferring Player Rating from Performance Data in Massively Multiplayer Online Role-Playing Games (MMORPGs)(2009-05-20) Shim, Kyong Jin; Pathak, Nishith; Srivastava, JaideepIn recent years, researchers have taken notice that virtual environments such as EverQuest II serve as a major mechanism for socialization. In particular, educational research has found virtual environments to be a sound venue for studying learning, collaboration, social participation, literacy in online space, and learning trajectory at the individual level as well as at the group level. The present research is concerned with learning in virtual environments and examines online player performance in EverQuest II, a popular massively multiplayer online role-playing game (MMORPG) developed by Sony Online Entertainment. The study uses the game's player performance data to devise performance metrics for online players. The study reports three major findings. First, we show that the game's point scaling system over-estimates performances of lower level players and under-estimates performances of higher level players. We present a novel point scaling system based on the game's player performance data that addresses the under-estimation and over-estimation problems. Second, we present a highly accurate predictive model for player performance as a function of past behavior. Third, we show that playing in groups has impact on player performance and that individual characteristics alone are not sufficient for explaining individual's performance, which calls for a different set of performance metrics methods. The discrepancy between the point scaling system in the game and observed player performance can be used as a guide to modify the existing system to better reflect the expected learning behaviors in different levels.Item Social Topic Models for Community Extraction(2008-02-11) Pathak, Nishith; DeLong, Colin; Erickson, Kendrick; Banerjee, ArindamWith social interaction playing an increasingly important role in the online world, the capability to extract latent communities based on such interactions is becoming vital for a wide variety of applications. However, existing literature on community extraction has largely focused on methods based on the link structure of a given social network. Such link-based methods ignore the content of social interactions, which may be crucial for accurate and meaningful community extraction. In this paper, we present a Bayesian generative model for community extraction which naturally incorporates both the link and content information present in the social network. The model assumes that actors in a community communicate on topics of mutual interest, and the topics of communication, in turn, determine the communities. Further, the model naturally allows actors to belong to multiple communities. The model is instantiated in the context of an email network, and a Gibbs sampling algorithm is presented to do inference. Through extensive experiments and visualization on the Enron email corpus, we demonstrate that the model is able to extract well-connected and topically meaningful communities. Additionally, the model extracts relevant topics that can be mapped back to corresponding real-life events involving Enron.Item StochColor: Stochastic Coloring based Graph Partitioning(2010-04-30) Pathak, Nishith; Banerjee, Arindam; Srivastava, JaideepGraph partitioning is a classical problem in computer science. Most algorithms consist of heuristic, spectral and stochastic flow based methods. In this paper a novel technique for graph partitioning is presented. The proposed algorithm, called StochColor extracts partitions from the most likely state of a stochastic graph coloring process. Empirical results show that StochColor is comparable to or significantly better than state of the art spectral clustering and stochastic flow based methods, across a variety of applications.Item Who Thinks Who Knows Who? Socio-cognitive Analysis of Email Networks(2006-07-21) Pathak, Nishith; Mane, Sandeep; Srivastava, JaideepInterpersonal interaction plays an important role in organizational dynamics, and understanding these interaction networks is a key issue for any organization, since these can be tapped to facilitate various organizational processes. However, the approaches of collecting data about them using surveys/interviews are fraught with problems of scalability, logistics and reporting biases, especially since such surveys may be perceived to be intrusive. Widespread use of computer networks for organizational communication provides a unique opportunity to overcome these difficulties and automatically map the organizational networks with a high degree of detail and accuracy. This paper describes an effective and scalable approach for modeling organizational networks by tapping into an organization's email communication. The approach models communication between actors as non-stationary Bernoulli trials and Bayesian inference is used for estimating model parameters over time. This approach is useful for socio-cognitive analysis (who knows who knows who) of organizational communication networks. Using this approach, novel measures for analysis of (i) closeness between actors' perceptions about such organizational networks (agreement), (ii) divergence of an actor's perceptions about organizational network from reality (misperception) are explained. Using the Enron email data, we show that these techniques provide sociologists with a new tool to understand organizational networks.