scholarly journals Integrated approach to detect spam in social media networks using hybrid features

Author(s):  
Kurapati Subba Reddy ◽  
E. Srinivasa Reddy

<p>Online social networking sites are becoming more popular amongst Internet users. The Internet users spend some amount of time on popular social networking sites like Facebook, Twitter and LinkedIn etc. Online social networks are considered to be much useful tool to the society used by Internet lovers to communicate and transmit information. These social networking platforms are useful to share information, opinions and ideas, make new friends, and create new friend groups. Social networking sites provide large amount of technical information to the users. This large amount of information in social networking sites attracts cyber criminals to misuse these sites information. These users create their own accounts and spread vulnerable information to the genuine users. This information may be advertising some product, send some malicious links etc to disturb the natural users on social sites. Spammer detection is a major problem now days in social networking sites. Previous spam detection techniques use different set of features to classify spam and non spam users. In this paper we proposed a hybrid approach which uses content based and user based features for identification of spam on Twitter network. In this hybrid approach we used decision tree induction algorithm and Bayesian network algorithm to construct a classification model. We have analysed the proposed technique on twitter dataset. Our analysis shows that our proposed methodology is better than some other existing techniques.</p>

Author(s):  
Anastasiia Zerkal ◽  
◽  
Viktoriia Holomb ◽  

The article considers the peculiarities of the formation of marketing communication strategies of the enterprise in terms of digitalization of the economy. The main directions of mass media in the twentieth century are determined and the delimitation of modern social media is presented. The conditions of compliance of the website have been determined so that it can be considered as a part of web 2.0: the ability to independently contribute to the content of the site; User control of your own information and website design -interactive and useful. The influence of digital and mobile technologies on the peculiarities of users' communication, as well as their attitude to the interactivity of social networks is proved. The potential of social networks to support their brands, increase the customer base and promote goods and services of enterprises has been identified. It is determined that due to its popularity, social networking sites have had a significant impact on ways of social communication and as a result have changed the sales channels of enterprises. It is estimated that the number of people using social networks is growing very fast, and at the time of writing, more than 2.62 billion people are using social networking sites. The largest social networks were analyzed: Facebook, Pinterest, Twitter, LinkedIn, Instagram. Their features and advantages for both users and professional marketers of enterprises are determined. It is estimated that in 2021, 71% of the total number of Internet users were users of social networks, and this percentage is projected to increase. The most popular activity among Internet users is social networking, and it has a high level of user engagement, which has a positive impact on the sales of businesses that work with digital marketing tools. The ease and low cost of Internet marketing compared to conventional advertising has proven that businesses in all sectors of the economy can more effectively reach their target audience, and social networks help influence other potential customers, and allow businesses to get useful feedback on their product or service. Ultimately, this leads to improved products / services and customer engagement, ie improves the company's marketing communication strategies in today's digital economy.


2016 ◽  
Vol 10 (2) ◽  
pp. 173-198
Author(s):  
Gun Gun Heryanto

Internet as a new media is a communication channel that can be a new public sphere. Especially after the migration of web 1.0 to web 2.0, internet users are connected to many social networking sites and interactive weblog to share informations, ideas and thought. It also allows the debate surrounding the Ahmadiyya get space between netizens. Polemic about Ahmadiyya no longer solely a matter of aqidah as a matter of prophecy, al Mahdi and al Masih, revelation, caliphate and jihad but also a matter of Human Rights (HAM) and the law. We need to map out the themes of the talk surrounding the Ahmadiyya among internet users as well as the need to know the context and dynamics of the evolving discourse on new media. This study traced 100 posts written by Internet users in Kompasiana during 2008-2012 as well as the data from the focus group discussion (FGD) with Kompasianer.


Author(s):  
George Veletsianos ◽  
Cesar Navarrete

<p>While the potential of social networking sites to contribute to educational endeavors is highlighted by researchers and practitioners alike, empirical evidence on the use of such sites for formal online learning is scant. To fill this gap in the literature, we present a case study of learners’ perspectives and experiences in an online course taught using the Elgg online social network. Findings from this study indicate that learners enjoyed and appreciated both the social learning experience afforded by the online social network and supported one another in their learning, enhancing their own and other students’ experiences. Conversely, results also indicate that students limited their participation to course-related and graded activities, exhibiting little use of social networking and sharing. Additionally, learners needed support in managing the expanded amount of information available to them and devised strategies and “workarounds” to manage their time and participation.<br /><strong></strong></p>


Author(s):  
Vladlena Benson

Based on the literature review of the theory of trust, this chapter aims to provide an insight into trust formation on social networking sites (SNS). An overview of the current state of cybercrime and known ways of threat mitigation helps shed some light on the reasons why social networks became easy targets for Internet criminals. Increasingly, personalisation is seen as a method for counteracting attacks perpetrated via phishing messages. This chapter aims to look specifically at trust in online social networks and how it influences vulnerability of users towards cybercrime. The chapter poses a question whether personalisation is the silver bullet to combat cyber threats on social networks. Further research directions are discussed.


2022 ◽  
pp. 791-802
Author(s):  
Sakshi Gupta ◽  
Neha Yadav ◽  
Loveleen Gaba

Recruitment has changed over the years. Organisations have started searching for an easy and cost effective platform for personality mining. With the explosion of social networking sites, candidates are now able to choose where they could spend their time online. This has encouraged many recruiters to start using social networking as part of a new cost-conscious approach to personality mining. Social networking websites function like an online community of internet users. Popular online sites include LinkedIn, Twitter, and Facebook. They are growing at an exponential rate, with most of the sites being free to join and, importantly, giving organizations an effective means of attracting today's Generation Y workforce. The purpose of this article is to contribute to emerging theory about the role of social networking sites in the process of personality mining.


2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Afifa Maryam ◽  
Usman Ahmed ◽  
Muhammad Aleem ◽  
Jerry Chun-Wei Lin ◽  
Muhammad Arshad Islam ◽  
...  

Smart phones are an integral component of the mobile edge computing (MEC) framework. Securing the data stored on mobile devices is very crucial for ensuring the smooth operations of cloud services. A growing number of malicious Android applications demand an in-depth investigation to dissect their malicious intent to design effective malware detection techniques. The contemporary state-of-the-art model suggests that hybrid features based on machine learning (ML) techniques could play a significant role in android malware detection. The selection of application’s features plays a very crucial role to capture the appropriate behavioural patterns of malware instances for a useful classification of mobile applications. In this study, we propose a novel hybrid approach to detect android malware, wherein static features in conjunction with dynamic features of smart phone applications are employed. We collect these hybrid features using permissions, intents, and run-time features (such as information leakage, cryptography’s exploitation, and network manipulations) to analyse the effectiveness of the employed techniques for malware detection. We conduct experiments using over 5,000 real-world applications. The outcomes of the study reveal that the proposed set of features has successfully detected malware threats with 97% F-measure results.


Author(s):  
Maryann Mori

This chapter provides an overview of the ways teens interact with social networking services. It acknowledges that teens are active users of social networking sites, and the implications of this usage affect and/or cross social, moral, educational and political lines. By reviewing current trends and statistics from various authors and sources, this chapter provides background information to understanding the growth and importance of online social networking among the Internet generation. Topics include demographics, ramifications on social behavior, adults’ concerns, policies designed to restrict teens’ Internet access, educational benefits and future directions of teens’ use of social networking services. Realizing the importance and influence of online social networks among teens should provide readers with a better understanding of how these sites can not only be used for educational and marketing purposes, but also be integrated within work environments.


2020 ◽  
Vol 15 (1) ◽  
pp. 226-228
Author(s):  
Scott Goldstein

A Review of: Jordan, K. (2019). Separating and merging professional and personal selves online: The structure and processes that shape academics’ ego-networks on academic social networking sites and Twitter. Journal of the Association for Information Science and Technology, 70(8), 830-842. https://doi.org/10.1002/asi.24170 Abstract Objective – To examine the structure of academics’ online social networks and how academics understand and interpret them. Design – Mixed methods consisting of network analysis and semi-structured interviews. Setting – Academics based in the United Kingdom. Subjects – 55 U.K.-based academics who use an academic social networking site and Twitter, of whom 18 were interviewed. Methods – For each subject, ego-networks were collected from Twitter and either ResearchGate or Academia.edu. Twitter data were collected primarily via the Twitter API, and the social networking site data were collected either manually or using a commercial web scraping program. Edge tables were created in Microsoft Excel spreadsheets and imported into Gephi for analysis and visualization. A purposive subsample of subjects was interviewed via Skype using a semi-structured format intended to illuminate further the network analysis findings. Transcripts were deductively coded using a grounded theory-based approach. Main Results – Network analysis replicated earlier findings in the literature. A large number of academics have relatively few connections to others in the network, while a small number have relatively many connections. In terms of reciprocity (the proportion of mutual ties or pairings out of all possible pairings that could exist in the network), arts and humanities disciplines were significantly more reciprocal. Communities (measured using the modularity algorithm, which looks at the density of links within and between different subnetworks) are more frequently defined by institutions and research interests on academic social networking sites and by research interests and personal interests on Twitter. The overall picture was reinforced by the qualitative analysis. According to interview participants, academic social networking sites reflect pre-existing professional relationships and do not foreground social interaction, serving instead as a kind of virtual CV. By contrast, Twitter is analogized to a conference coffee break, where users can form new connections. Conclusion – Academic social networking sites exhibit networks that are smaller, denser, more clustered around discrete modularity classes, and more reciprocal. Twitter networks are larger and more diffuse, which is more conducive to fostering novel connections. The author makes suggestions for how academic social networking sites could encourage network building and rethink how academic reputation is measured.


Author(s):  
Élodie Verseillié ◽  
Stéphanie Laconi ◽  
Henri Chabrol

Background: With a growing number of users, social networking sites have been the subject of numerous recent studies, but little investigation has been given to their problematic use. Objectives: Our main objective was to study the relationship between psychopathological variables (i.e., personality traits, depressive and anxiety symptoms, and stress) and problematic Facebook and Twitter use. Participants and method: A sample of 1068 Internet users (Mage = 26.64; SD = 9.5) has been recruited online. Participants completed scales exploring problematic Facebook and Twitter use, and psychopathological variables. Results: Problematic Facebook and Twitter use were predicted by different pathological personality traits, regrouped in clusters in our study. Depressive and anxiety symptoms were also predictive of problematic Facebook and Twitter use but only stress explained problematic Facebook use. Gender differences have been observed. Discussion: This study highlights the relationship between depression, anxiety, stress, pathological personality traits, and problematic Facebook and Twitter use. Significant differences have been retrieved between these two uses and their relationship to psychopathology. Future research should also explore the causal relationship between social networking sites use and psychopathology and consider gender.


First Monday ◽  
2011 ◽  
Author(s):  
Chris Fullwood ◽  
Mike Thelwall ◽  
Sam O'Neill

With the increasing popularity of social networking sites, it has become relatively common for Internet users to develop an online presence via a personal profile page. Moreover, some chat rooms allow members to develop profile pages too. As a potential first point of contact, effective profile construction may play a pivotal role in the management of first impressions. Identity construction in profiles seems to be particularly important for chat room users, because they are often likely to interact with strangers. Since chat rooms can be used for anti-social purposes, the type and extent of the information posted in chat room profiles seems likely to be different from that in online profiles for social networking sites, which may be more closely tied to offline identities. This investigation of information in 324 profiles from two Lycos chat rooms for adults found that most users include a picture of themselves on their profile, hence apparently tying themselves to their offline identity. Nevertheless, the majority remain anonymous, probably many more than for social networking sites and blog authors. There are sex differences in the types of information posted on chat room profiles, with women tending to include more personal information. Furthermore, older users are more likely to post information about relationship status and location than younger users. These sex and age differences in profile content may be a consequence of the different motivations for using the service as well as disparities in self-disclosure norms.


Sign in / Sign up

Export Citation Format

Share Document