International Journal of Web Based Communities (8 papers in press)
Plague of Cross-Site Scripting on the Web Applications: A Review, Taxonomy and Challenges
by Brij Gupta, Pooja Chaudhary
Prediction of Missing Links in a Social Networks: FINN (Feature Integration with Node Neighbor)
by ANAND GUPTA, Neetu Sardana
Abstract: Link prediction techniques are used to identify the future network structure on the basis of existing connectivity pattern of the users. Most of the existing link prediction techniques employ varied similarity indices to predict new links in network. Some techniques use common neighbors while others use common shared profile information of the user for prediction. Typically existing link prediction techniques have only focused on one of these two data modalities: common neighbors or common attributes. Both of them play equally important role in the dynamics of the network. In this paper, we propose a Feature Integrated Node Neighbor (FINN) approach, an accurate algorithm for predicting links in network. FINN integrates Jaccard coefficient and Adamic Adar to predict link between nodes using their connections and features. We have evaluated FINN by implementing it over the real-time Facebook dataset collected from SNAP repository and validated the result through area under ROC curve.
Keywords: Link prediction; Social network; Feature integration with node neighbor (FINN); Jaccard index; Adamic adar index; Cosine Similarity; Similarity indices.
Multi Process Prediction Model (MPPM) for Customer Behaviour Analysis
by D. KALAIVANI, P. Sumathi, Arunkumar Thangavelu
Abstract: Online Purchase is one of the big changes to the retail marketing. As the lifestyle changed, the people are not going to shops for purchasing required items like gifts, accessories or any electronic items. Everyone started to use online and saving their time, effort and money.They gain a good offer through online shopping. Online shopping helps the customer to know the price of the item in advance and able to compare the price with different vendors. It helps the customer to buy the item from the vendor who offers the item with low-cost and good quality. Customer behaviour analysis is very much needed to help the vendors to define their strategy for online shopping, advertising, market segmentation and so on.This work focuses on analyzing customer behavior analysis using the internet usage of the customer and amount spent by the customer while shopping the item through online.
Keywords: Online Shopping; Data Mining; Market Segmentation; Advertising; Multivariate Analysis; Customer Behaviour Analysis; Advertisement; Linear Regression,Retail Marketing.
Understanding Empowerment in Social Media Context: Lessons from Indonesian Migrant Domestic Workers
by Stevanus Wijaya, Christine Bruce, Jason Watson
Abstract: This paper presents shared practices amongst Indonesian migrant users of an online community hosted in Facebook which potentially empower them. We conducted a virtual ethnography study which was comprised of online observations and interviews. The results show that shared practices within the online community empower migrants by enhancing their psychological wellbeing, and awareness of migrant
Keywords: migrant domestic workers; virtual ethnography; social media; empowerment; online community; Facebook.
Twitting Bad Rumors - the Grexit Case
by Dimitrios Kydros
Abstract: In this paper, we use methods from social network analysis to investigate patterns in data regarding the spreading of rumours regarding serious economic situations. More specifically, we use data acquired from Twitter during a period of time regarding keyword grexit. We then investigate a number of parameters regarding these data, such as their volume over time and their time relevance according to news feeds. We proceed by using methods from social network analysis (SNA) in order to create networks of tweets. These networks are comprised of persons or institutions that circulated globally our keyword of interest. The networks are then analysed according to well established methods and metrics from SNA. A certain approach tries to distinguish twitters from Greece and all other countries, when possible. Nodes are also clustered in communities, followed by another discussion on the way they interact and/or influence each other. Finally, we try to create a second class of network, regarding the semantics of the tweets
Keywords: grexit; social network analysis; twitter; economic crisis; semantic networks.
Applying resource mobilization and political process theories to explore social media and environmental protest in contemporary China
by Hua Pang
Abstract: While increased attention has been given to the frequent occurrence of large-scale environmental movements, the role that the new information and communication technology, especially social media, plays in these environmental collective actions has rarely been systematically investigated. The article represents one of the few that seeks to examine the utility of social media in the recent environment protection and explore how the innovative media can mobilise environmental protests through the perspective of resource mobilisation and political process theories. The outcomes show that the newly emerging social media is not only a valuable resource for collective action and the organisation of online civil mobilisation, but also plays an instrumental role in the opposition to major policies that may lead to the change of the government decisions. The study may have practical significance and academic value for understanding the new media field and online environmental protest in contemporary China.
Keywords: social media; case study; environmental protest; resource mobilization theory; political process theory; China.
USAGE FACTORS OF LOCATION-BASED SOCIAL APPLICATIONS: THE CASE OF FOURSQUARE
by Aysun Bozanta, Mustafa Coskun, Birgul Kutlu
Abstract: Location-based social applications allow users to share their locations in a rich media context, keep in touch with friends and find new places to explore. Studies that investigate the usage factors of location-based social applications are either qualitative or based on application data. In this study, Foursquare, a highly popular mobile location-based social network, was analysed from the perspective of users. This study contributes to the field by employing E-TAM to identify the effects of perceived usefulness, perceived ease of use, perceived enjoyment and social connection in Foursquare usage within the framework of structural equation modelling. The results of the online survey with 233 responses showed that perceived ease of use and perceived enjoyment have a direct and significant impact on actual Foursquare usage, while social connection indirectly affects. Perceived usefulness, on the other hand, has no impact on the actual usage of Foursquare.
Keywords: Location-based Social Network; Foursquare; Structural Equation Modeling; Technology Acceptance Model.
Elimination of Backward Browsing using Decomposition and Compression for Efficient Navigation Prediction
by Neetu Sardana, Honey Jindal
Abstract: Analysing the user's browsing patterns stored in weblog file can help in providing the personalised environment, improving website structure and recommending the suitable navigation pattern. While browsing the web, the user navigates in a forward direction following the web topology, results in the session having correlated web pages. Backward navigation takes place when the user returns to the previously visited page. This traversal results in increased session length, complexity and reduction in the prediction accuracy. The frequent backward movement also infers that the web community is not well structured. Therefore, to discover the meaningful browsing pattern and improve the website structure, it is essential to filter the repeated web pages from the session. This paper proposes two novel backward elimination techniques: decomposed backward browsing (BBDcom) and compressed backward browsing (BBcom). BBDcom reduces the length of a session using decomposition. It can restore the original session without losing data. BBcom compresses the session length by eliminating web page(s) lying in between the redundant web pages. The experimental result shows that proposed techniques improve the prediction accuracy and reduces the state-space complexity.
Keywords: Sessions; Navigation; Prediction; Markov; Web; Web community; Backward; Forward; Accuracy.