if you want the project pls call @8125424511
Spammer Detection and Fake User Identification on Social Networks
ABSTRACT
Social networking sites engage millions of users around the world. The users' interactions with these social sites, such as Twitter and Facebook have a tremendous impact and occasionally undesirable repercussions for daily life. The prominent social networking sites have turned into a target platform for the spammers to disperse a huge amount of irrelevant and deleterious information. Twitter, for example, has become one of the most extravagantly used platforms of all times and therefore allows an unreasonable amount of spam. Fake users send undesired tweets to users to promote services or websites that not only affect legitimate users but also disrupt resource consumption. Moreover, the possibility of expanding invalid information to users through fake identities has increased those results in the unrolling of harmful content. Recently, the detection of spammers and identification of fake users on Twitter has become a common area of research in contemporary online social Networks (OSNs). In this paper, we perform a review of techniques used for detecting spammers on Twitter. Moreover, a taxonomy of the Twitter spam detection approaches is presented that classifies the techniques based on their ability to detect: (i) fake content, (ii) spam based on URL, (iii) spam in trending topics, and (iv) fake users. The presented techniques are also compared based on various features, such as user features, content features, graph features, structure features, and time features.We are hopeful that the presented study will be a useful resource for researchers tofind the highlights of recent developments in Twitter spam detection on a single platform.
EXISTING SYSTEM
v Shen et al. [29] investigated issues of detecting spammers on Twitter. The proposed method combines characteristics withdrawal from text content and information of social networks. The authors used matrix factorization to determine the underline feature matrix or the tweets and then came up with a social regularization with interaction coefficient to teach the factorization of the underline matrix. Subsequently, the authors combined knowledge with social regularization and factorization matrix processes, and performed experiments on the real-world Twitter dataset, i.e., UDI Twitter dataset.
v Washha et al. [31] described the Hidden Markov Model for filtering the spam related to recent time. The method supports the accessible and obtainable information in the tweet object to recognize spam tweets and the tweets that are handled previously related to the same topic.
v Jeong et al. [17] analyzed the follow spam on Twitter as an alternative of dispersion of provoking public messages, spammers follow authorized users, and followed by authorized users. Categorization techniques were proposed that are used for the detection of follow spammers. The focus of the social relation is cascaded and formulated into two mechanism, i.e., social status filtering and trade significance
v profile filtering, where each of which uses two-hop sub networks that are centered at each other. Assemble techniques and cascading filtering are also proposed for combining the properties of both trade significance profile and social status. To check whether a user is fake or not, a two-hop social network for each user is focused to gather social information from social networks.
v Meda et al. [21] presented a technique that utilizes a sampling of non-uniform features inside a machine learning system by the adaptation of random forest algorithm to recognize spammer insiders. The proposed framework focuses on the random forest and non-uniform feature sampling techniques. The random forest is a learning algorithm for the categorization and regression that works by assembling several decision trees at preparation time and selecting the one with the majority votes by individual trees. The scheme integrates bootstrap aggregating technique with the un-planned selection of features.
Disadvantages
o There is no filtering system based on a preprocessing schedule and on Naïve Bayes algorithm to discard the tweets containing inaccurate information,.
o Less security due No URL Based Spam Detection.
PROPOSED SYSTEM
v In the proposed system, the system elaborates a classification of spammer detection techniques. The system shows the proposed taxonomy for identification of spammers on Twitter. The proposed taxonomy is categorized into four main classes, namely, (i) fake content, (ii) URL based spam detection, (iii) detecting spam in trending topics, and (iv) fake user identification. Each category of identification methods relies on a specific model, technique, and detection algorithm.
v The first category (fake content) includes various techniques, such as regression prediction model, malware alerting system, and Lfun scheme approach. In the second category (URL based spam detection), the spammer is identified in URL through different machine learning algorithms. The third category (spam in trending topics) is identified through Naïve Bayes classifier and language model divergence. The last category (fake user identification) is based on detecting fake users through hybrid techniques.
Advantages
Ø The average numbers of verified accounts that were either spam or non-spam and (ii) the number of followers of the user accounts.
Ø The fake content propagation was identified through the metrics that include: (i) social reputation, (ii) global engagement, (iii) topic engagement, (iv) likability, and (v) credibility. After that, the authors utilized regression prediction model to ensure the overall impact of people who spread the fake content at that time and also to predict the fake content growth in future.
SYSTEM REQUIREMENTS
➢ H/W System Configuration:-
➢ Processor - Pentium –IV
➢ RAM - 4 GB (min)
➢ Hard Disk - 20 GB
➢ Key Board - Standard Windows Keyboard
➢ Mouse - Two or Three Button Mouse
➢ Monitor - SVGA
SOFTWARE REQUIREMENTS:
v Operating system : Windows 7 Ultimate.
v Coding Language : Python.
v Front-End : Python.
v Back-End : Django-ORM
v Designing : Html, css, javascript.
v Data Base : MySQL (WAMP Server).
thank you for your comment
pls call me on 8125424511