مقاله انگلیسی رایگان در مورد تشخیص اسپم ها در بازاریابی توییتر – اسپرینگر 2017

Customer engagement is drastically improved through Web 2.0 technologies, especially social media platforms like Twitter. These platforms are often used by organizations for marketing, of which creation of numerous spam profiles for content promotion is common. The present paper proposes a hybrid approach for identifying the spam profiles by combining social media analytics and bio inspired computing. It adopts a modified K-Means integrated Levy flight Firefly Algorithm (LFA) with chaotic maps as an extension to Firefly Algorithm (FA) for spam detection in Twitter marketing. A total of 18,44,701 tweets have been analyzed from 14,235 Twitter profiles on 13 statistically significant factors derived from social media analytics. A Fuzzy C-Means Clustering approach is further used to identify the overlapping users in two clusters of spammers and non-spammers. Six variants of K-Means integrated FA including chaotic maps and levy flights are tested. The findings indicate that FA with chaos for tuning attractiveness coefficient using Gauss Map converges to a working solution the fastest. Further, LFA with chaos for tuning the absorption coefficient using sinusoidal map outperforms the rest of the approaches in terms of accuracy.

Introduction

Use of social media platforms like Twitter, Facebook, YouTube, Instagram and LinkedIn etc. is indispensable for information diffusion in the current world (Kaplan and Haenlein 2010; Lenhart et al. 2010; Mui and Whoriskey 2010). The platforms are being used by the people for communicating their opinions, experiences and ideas and are faster than traditional media in diffusion of information (Bakshy et al. 2012). Following individual users, organizations and businesses are also present in the platforms to connect with different stakeholders. The profiles of businesses are predominantly for content promotion and knowledge dissemination surrounding products and services, making the social media platforms the backbone of digital marketing. The social media presence is utilized to promote the content to a larger audience (Hanna et al. 2011). Needless to say that platforms are now flooded with information from various sources by multiple organizations competing for the users’ attention (Romero et al. 2011). Among the social platforms, Twitter is one of the fasting growing micro blogging platforms that helps people communicate and share their opinion using short messages (Huberman et al. 2008). The extant knowledge highlights that about 54% of the Fortune 50 organizations have Twitter account and 37% of these have multiple profiles. Further, 85% of these organizations use Twitter for news dissemination (Case and King 2011). When compared among social media platforms, Twitter has the highest usage for business (78%), followed by LinkedIn (74%), and Facebook (44%) (Go and You 2016). These high usage statistics of Twitter by businesses and organizations pose greater risk of spams. Twitter by itself uses verified accounts for profiles of various celebrities, political figures and organizations but it is only 0.061% of all Twitter accounts.