Recommending Related Microblogs

Computing similarity between short microblogs is an important step in microblog recommendation. In this chapter, the authors utilize three kinds of approaches—traditional term-based approach, WordNet-based semantic approach, and topic-based approach—to compute similarities between micro-blogs and recommend top related ones to users. They conduct experimental study on the effectiveness of the three approaches in terms of precision. The results show that WordNet-based semantic similarity approach has a relatively higher precision than that of the traditional term-based approach, and the topic-based approach works poorest with 548 tweets as the dataset. In addition, the authors calculated the Kendall tau distance between two lists generated by any two approaches from WordNet, term, and topic approaches. Its average of all the 548 pair lists tells us the WordNet-based and term-based approach have generally high agreement in the ranking of related tweets, while the topic-based approach has a relatively high disaccord in the ranking of related tweets with the WordNet-based approach.

Local Community Extraction in Social Network Analysis

To identify global community structures in networks is a great challenge that requires complete information of graphs, which is infeasible for some large networks, e.g. large social networks. Recently, local algorithms have been proposed to extract communities for social networks in nearly linear time, which only require a small part of the graphs. In local community extraction, the community extracting assignments are only done for a certain subset of vertices, i.e., identifying one community at a time. Typically, local community detecting techniques randomly start from a vertex and gradually merge neighboring vertices one-at-a-time by optimizing a measure metric. In this chapter, plenty of popular methods are presented that are designed to obtain a local community for a given graph.

Analyzing Social Networks to Mine Important Friends

The emergence of Web-based communities and social networking sites has led to a vast volume of social media data, embedded in which are rich sets of meaningful knowledge about the social networks. Social media mining and social network analysis help to find a systematic method or process for examining social networks and for identifying, extracting, representing, and exploiting meaningful knowledge—such as interdependency relationships among social entities in the networks—from the social media. This chapter presents a system for analyzing the social networks to mine important groups of friends in the networks. Such a system uses a tree-based mining approach to discover important friend groups of each social entity and to discover friend groups that are important to social entities in the entire social network.

Topic Modeling for Web Community Discovery

The proliferation of the Web has led to the simultaneous explosive growth of both textual and link information. Many techniques have been developed to cope with this information explosion phenomenon. Early efforts include the development of non-Bayesian Web community discovery methods that exploit only link information to identify groups of topical coherent Web pages. Most non-Bayesian methods produce hard clustering results and cannot provide semantic interpretation. Recently, there has been growing interest in applying Bayesian-based approaches to discovering Web community. The Bayesian approaches for Web community discovery possess many good characteristics such as soft clustering results and ability to provide semantic interpretation of the extracted communities. This chapter presents a systematic survey and discussions of non-Bayesian and Bayesian-based approaches to the Web community discovery problem.

Supporting Social Interaction in Campus-Scale Environments by Embracing Mobile Social Networking

With the popularity of smart phones, the warm embrace of social networking services, and the perfection of wireless communication, mobile social networking has become a hot research topic. The characteristics of mobile devices and requirements of services in social environments pose challenges to the construction of a social platform. In this chapter, the authors elaborate a flexible system architecture based on the service-oriented specification to support social interaction in a university campus. For the client side, they designed a mobile middleware to collect social contexts such as proximity, acceleration, and cell phone logs, etc. The server backend aggregates such contexts, analyzes social connections among users, and provides social services to facilitate social interaction. A prototype of mobile social networking system is deployed on campus, and several applications are implemented to demonstrate the effectiveness of the proposed architecture. Experiments were carried out to evaluate the performance (in terms of response time and energy consumption) of our system. A user study was also conducted to investigate user acceptance of our prototype. The experimental results show that the proposed architecture provides real-time response to users. Furthermore, the user study demonstrates that the applications are useful to enhance social interaction in campus environments.

Tag Cloud Reorganization

Tag clouds have become an appealing way of navigating through Web pages on social tagging systems. Recent research has focused on finding relations among tags to improve visualization and access to Web documents from tag clouds. Reorganizing tag clouds according to tag relatedness has been suggested as an effective solution to ease navigation. Most of the approaches either rely on co-occurrences or rely on textual content to represent tags. In this chapter, the authors explore tag cloud reorganization based on both of them. They compare these clouds from a qualitative point of view, analyzing pros and cons of each approach. The authors show encouraging results suggesting that co-occurrences produce more compelling reorganization of tag clouds than textual content, being computationally less expensive.

Method for Modeling User Semantics and its Application to Service Navigation on the Web

The value of information accumulated on the Web is enhanced when it is provided to the user who faces a problematic situation that can be solved by the information. The authors have investigated a task-oriented menu that enables users to search for mobile Internet services not by category but by situation. Construction of the task-oriented menu is based on a user modeling method that supports descriptions of user activities, such as task execution and defeating obstacles encountered during the task, which in turn represents the users’ situations and/or needs for certain information. They built task models of the mobile users that cover about 97% of the assumed situations of mobile Internet services. Then they reorganized “contexts” in the model and designed a menu hierarchy from the viewpoint of the task. The authors have linked the designed menu to the set of mobile Internet service sites included in the i-mode service operated by NTT docomo, consisting of 5016 services. Among them, 4817 services are properly connected to the menu. This chapter introduces a framework for a real scale task-oriented menu system for mobile service navigation with its relations to the SNS applications as knowledge resources.

News Document Summarization Driven by User-Generated Content

Experiments performed on real collections of news articles and driven by on-topic Twitter posts show the effectiveness of the proposed approach.

Mobile Context Data Mining

The mobile devices, such as iPhone, iPad, and Android are becoming more popular than ever before. Many mobile-based intelligent applications and services are emerging, especially those location-based and context-aware services, e.g. Foursquare and Google Latitude. The mobile device is important since it can detect a user’s rich context information with its in-device sensors, e.g. GPS, Cell ID, and accelerometer. With such data and suitable data mining methods better understanding of users is possible; smart and intelligent services thus can be provided. In this chapter, the authors introduce some mobile context mining applications and methods. To be specific, they first show some typical mobile context data types with a mobile phone which can be detected. Then, they briefly introduce mining methods that are related to two mostly used types of mobile context data, location, and accelerometer. In the following, we illustrate in detail two context data mining methods that process multiple types of context data and can deal with the more general problem of user understanding: how to mine users’ behavior patterns and how to model users’ significant contexts from the users’ mobile context log. In each section, the authors show some state-of-the-art works.

Clustering Algorithms for Tags

With the development and application of social media, more and more user-generated contents are created. Tag data, a kind of typical user generated content, has attracted lots of interests of researchers. In general, tags are the freely chosen textual descriptions by users to label digital data sources in social tagging systems. Poor retrieval performance remains a major problem of most social tagging systems resulting from the severe difficulty of ambiguity, redundancy, and less semantic nature of tags. Clustering method is a useful tool to increase the ability of information retrieval in the aforementioned systems. In this chapter, the authors (1) review the background of state-of-the-art tagging clustering and the tag data description, (2) present five kinds of tag similarity measurements proposed by researchers, and (3) finally propose a new clustering algorithm for tags based on local information that is derived from Kernel function. This chapter aims to benefit both academic and industry communities who are interested in the techniques and applications of tagging clustering.