International Research Journal of Engineering and Technology (IRJET) Volume: 09 Issue: 05 | May 2022
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
DETECTION OF MALICIOUS SOCIAL BOTS USING ML TECHNIQUE IN TWITTER NETWORK V N P SAI SIRI DANTU 1 , JHANSI DEVI TELU2 ,PADMA SREE KUNCHAM 3 ,GURUDATTA PILLA 4 1234 Final
Year B.Tech, CSE, Sanketika Vidya Parishad Engineering College, Visakhapatnam,A.P, India Guided by: Mrs. Gudiwaka Vijayalakshmi, Associate Professor, SVPEC, Visakhapatnam, A.P, India -----------------------------------------------------------------------***-----------------------------------------------------------------------
topics. Hence, users can get informed about the hot topics of discussion on a daily basis. And generally online social networks (OSNs) are increasingly used by automated accounts, well known as bots, due to their immense popularity across a wider range of user categories.It is estimated that over 15% of accounts on Twitter are automated bot accounts.A customer support chatbot is a prime example of a Twitter bot.It can help and improve the overall customer support experience by improving the response time. Following few are the most useful and amazing bots on Twitter.
ABSTRACT: Malicious (spam) social bots generate and spread fake tweets and automate their social relationships by pretending like a follower and by creating multiple fake accounts with malicious activities. Furthermore, malicious social bots post shortened malicious URLs in the tweet in order to redirect the requests of online social networking participants to some malicious and suspicious servers. Hence, distinguishing malicious social bots from legitimate users is one of the most tasks in the Twitter network. To detect malicious or suspicious social bots, extracting URL-based features that include frequency of shared URLs, DNS fluxiness feature, network features, link popularity features and spam content presents in URLrequires less amount of time comparatively with social graph-based features (which rely on the social interactions of users). Moreover, malicious social bots cannot quickly manipulate URL redirection chains. In this, a learning automata-based malicious social bot detection (LA-MSBD) algorithm is a Machine Learning approach proposed by integrating a NaĂŻve Bayes algorithm model with URL-based features(URL Classification and Feature Extraction) for identifying trustworthy participants (users) in the Twitter network. Experimentation has been performed on 2 Twitter data sets, and the results obtained illustrate that the proposed algorithm achieves improvement in precision and detection accuracy.
@HundredZeros: Twitter bot that frequently recommends amazing and thought provoking e-books that are free on Amazon. This helps followers and avid readers find great titles and content to read. @MagicRealismBot: Magic realism is quite an amusing Twitter bot that argues the existence and significance of magic in the real world. The tweets posted by this bot are some of the funniest tweets that one can find. @DearAssistant: Virtual Assistants (Google Assistant, Siri, Alexa) became the most used medium to extract relevant information in any aspects. @DearAssistant is a Twitter bot developed to provide answers to questions like the definition of words, the distance between places, and many other things. There do exists different facet of those automatic bots which ends in a very nice loss. Spam bots faux like legitimate users by making pretend accounts and IDâs and posting same tweets repeatedly and spreading pretend news and conjointly tweets which will aid to malicious servers and successively ends up in forceful consequences. Their main purpose is that the dissemination of pretend news, the promotion of specific ideas and merchandise, the manipulation of the securities market. By posting tweets very often, they influence measures together with the trending topics. As a consequence, legitimate users cannot distinguish between real trending topics and pretend ones. In Twitter, once a participant (user) desires to share a tweet containing URL(s) with the neighboring participants (followers or followees), the participant adapts uniform resource locator shortened service so as to cut back the length of uniform resource locator (because a tweet is restricted up to one hundred forty
KEY WORDS: Learning Automata, URLfeatures, Malicious Social Bots, URL Classification, Feature Extraction, Online social network.
INTRODUCTION Twitter being a micro-blogging platform used by an increasing population of users of different age groups over the last decade. Generally, people post tweets and interact with other users as well. More specifically, they (users) can follow (following/friends) their favorite politicians, celebrities, athletes, entrepreneur, artists, friends and get followed by them (followers). Furthermore, Twitter generates a list of the topics being discussed day-to-day updates, that so called trending
© 2022, IRJET
|
Impact Factor value: 7.529
|
ISO 9001:2008 Certified Journal
|
Page 880