User Segmentation Based on Twitter Data Using Fuzzy Clustering

Social Networking Sites, which create platform for social interactions and sharing are the mostly used internet websites, thus are very important in today’s world. The vast usage of social networking sites (SNSs) has effected the business world, new business models are proposed, business process are renewed and companies try to create benefit form these sites. Besides the functional usage of SNSs such as marketing and customer relations, companies can create value by analyzing and mining the data on SNSs. In this paper, a new segmentation approach, using Text Mining and Fuzzy Clustering techniques. Text mining is process of extracting knowledge from large amounts of unstructured data source such as content generated by the SNSs users. Fuzzy clustering is an algorithm for cluster analysis in which the allocation of data points to clusters is fuzzy. In the proposed approach, users self description text are used as an input to the Text Mining process, and Fuzzy Clustering is used to extract knowledge from data. Using the proposed approach, companies can segment their customers based on their comments, ideas or any kind of other unstructered data on SNSs.

Social Media Analytics

Many popular online social networks such as Twitter, LinkedIn, and Facebook have become increasingly popular. In addition, a number of multimedia networks such as Flickr have also seen an increasing level of popularity in recent years. Many such social networks are extremely rich in content, and contain tremendous amount of content and linkage data which can be leveraged for analysis. The linkage data is essentially the graph structure of the social network and the communications between entities; whereas the content data contains the text, images and other multimedia data in the network. The growth of the usage and penetration of social media in the recent years has been enormous and unprecedented. This significant increase in its usage and increased number of users, there has been trend of a substantial increase in the volume of information generated by users of social media. Irrespective of primary domain in which organization is operating in to, whether it is insurance sector, social media (including facebook, twitter etc), medical science, banking etc. Virtually a large number of varying nature and services of organizations are making significant investments in social media. But it is also true that many are not systematically analyzing the valuable information that is resulting from their investments. This chapter aims at providing a data-centric view of online social networks; a topic which has been missing from much of the literature and to draw unanswered research issues which can be further explored to strengthen this area.

Defining the Factors that Effect User Interest on Social Network News Feeds via Fuzzy Association Rule Mining

Social networking became one of the main marketing tools in the recent years since it’s a faster and cheaper way to reach the customers. Companies can use social networks for efficient communication with their current and potential customers but the value created through the usage of social networks depends on how well the organizations use these tools. Therefore a support system which will enhance the usage of these tools is necessary. Fuzzy Association rule mining (FARM) is a commonly used data mining technique which focuses on discovering the frequent items and association rules in a data set and can be a powerful tool for enhancing the usage of social networks. Therefore the aim of the chapter is to propose a fuzzy association rule mining based methodology which will present the potential of using the FARM techniques in the field of social network analysis. In order to reveal the applicability, an experimental evaluation of the proposed methodology in a sports portal will be presented.

Analysing the Performance of a Fuzzy Lane Changing Model Using Data Mining

Heavy vehicles have substantial impact on traffic flow particularly during heavy traffic conditions. Large amount of heavy vehicle lane changing manoeuvres may increase the number of traffic accidents and therefore reduce the freeway safety. Improving road capacity and enhancing traffic safety on freeways has been the motivation to establish heavy vehicle lane restriction strategies to reduce the interaction between heavy vehicles and passenger cars. In previous studies, different heavy vehicle lane restriction strategies have been evaluated using microscopic traffic simulation packages. Microscopic traffic simulation packages generally use a common model to estimate the lane changing of heavy vehicles and passenger cars. The common lane changing models ignore the differences exist in the lane changing behaviour of heavy vehicle and passenger car drivers. An exclusive fuzzy lane changing model for heavy vehicles is developed and presented in this chapter. This fuzzy model can increase the accuracy of simulation models in estimating the macroscopic and microscopic traffic characteristics. The results of this chapter shows that using an exclusive lane changing model for heavy vehicles, results in more reliable evaluation of lane restriction strategies.

Critical Parameters for Fuzzy Data Mining

Research on data mining is increasing at an incessant rate and to improve its effectiveness other techniques have been applied such as fuzzy sets, rough set theory, knowledge representation, inductive logic programming, or high-performance computing. Fuzzy logic due to its proficiency in handling uncertainty has gained its importance in a variety of applications in combination with the use of data mining techniques. In this chapter we take this association a notch further by examining the parameters which allow fuzzy sets and data mining to be combined into what has come to be known as fuzzy data mining. Analyzing and understanding these critical parameters is the main purpose of this chapter, so as to acquire maximum efficiency in applying the same which impelled the authors to work extensively and find out the crucial parameters essential to the application of fuzzy data mining.

Semantic Integrating for Intelligent Cloud Data Mining Platform and Cloud Based Business Intelligence for Optimization of Mobile Social Networks

In this chapter, the authors focused on optimization of MSNs based on integrating for intelligent DM and BI platforms, which involves mobile devices. The approach is defining the challenges based social network trends and current situation explorations, and then applying the techniques to exploring the social media towards social cloud technology, which focused on creating a scalable, adaptable and optimal social cloud as the users’ contexts and IT technologies. The newly proposed method is vigorously significant to develop flexible social networking in relation to the development of IT, which facilitates data/information access, distributions, high availability and a large amount of data analysis and others. Therefore, the techniques this chapter is vitally crucial to improve the performance and use of social networking in a comprehensive and powerful way. Nutshell, this chapter overviews the impetus for the development of intelligent semantic cloud and diversified social-networking in both physical and wireless sectors, which representing a wide aspect of social cloud change, and increasingly appropriate service providing a platform for innovative ideas and technological innovation in the business environment.

Dynamic Social Network Mining

This Chapter overviews most recent data mining approaches proposed in the context of social network analysis. In particular, it aims at classifying the proposed approaches based on both the adopted mining strategies and their suitability for supporting knowledge discovery in a dynamic context. To provide a thorough insight into the proposed approaches, main work issues and prospects in dynamic social network analysis are also outlined.

Need for Dynamicity in Social Networking Sites

This chapter presents this new emerging technology of social media and networking with a detailed discussion on: basic definitions and applications, how this technology evolved in the last few years, the need for dynamicity under data mining environment. It also provides a comprehensive design and analysis of popular social networking media and sites available for the users. A brief discussion on the data mining methodologies for implementing the variety of new applications dealing with huge/big data in data science is presented. Further, an attempt is being made in this chapter to present a new emerging perspective of data mining methodologies with its dynamicity for social networking media and sites as a new trend and needed framework for dealing with huge amount of data for its collection, analysis and interpretation for a number of real world applications. A discussion will also be provided for the current and future status of data mining of social media and networking applications.

New Trends in Fuzzy Clustering

Fuzzy methodologies show progress day by day towards better explanation of various natural, social, engineering and information problem solutions in the best, economic, fast and effective manner. This chapter provides cluster analyses from probabilistic, statistical and especially fuzzy methodology points of view by consideration of various classical and innovative cluster modeling and inference systems. After the conceptual assessment explanation of fuzzy logic thinking fundamentals various clustering methodologies are presented with brief revisions but innovative trend analyses as k-mean-standard deviation, cluster regression, relative clustering for depiction of trend components that fall within different clusters. The application of fuzzy clustering methodology is presented for lake time series and earthquake modeling for rapid hazard assessment of existing buildings.

Data Mining Prospects in Mobile Social Networks

Unable to accommodating new technologies, including social technology, mobile devices and computing are other potential problems, which are significant challenges to social-networking service. The very broad range of such social-networking challenges and problems are demanding advanced and dynamic tools. Therefore, in this chapter, we introduced and discussed data mining prospects to overcome the traditional social-networking challenges and problems, which led to optimization of MSNs application and performances. The proposed method infers defining and investigating social-networking problems using data mining techniques and algorithms based on the large-scale data. The approach is also exploring the possible potential of users and systems contexts, which leads to mine the personal contexts such as the users’ locations and situations from the mobile logs. In these sections, we discussed and introduced new ideas on social technologies, data mining techniques and algorithm’s prospects, social technology’s key functional and performances, which include social analysis, security and fraud detections by presenting a brief analysis, and modeling based descriptions. The approach also empirically discussed using the real survey data, which the result showed how data mining vitally significant to explore MSNs performance and its crosscutting impacts. Finally, this chapter provides fundamental insight to researchers and practitioners who need to know data mining prospects and techniques to analyze large, complex and frequently changing data. This chapter is also providing a state-of-the-art of data mining techniques and algorithm’s dynamic prospects.