Exploring friend's influence in cultures in Twitter

Abstract

What does a user do when he logs in to the Twitter website? Does he merely browse through the tweets of all his friends as a source of information for his own tweets, or does he simply tweet a message of his own personal interest? Does he skim through the tweets of all his friends or only of a selected few? A number of factors might influence a user in these decisions. Does this social influence vary across cultures? In our work, we propose a simple yet effective model to predict the behavior of a user -in terms of which hashtag or named entity he might include in his future tweets. We have approached the problem as a classification task with the various influences contributing as features. Further, we analyze the contribution of the weights of the different features. Using our model we analyze data from different cultures and discover interesting differences in social influence. II. INTRODUCTIONCultures vary on the amount of emphasis they give on encouraging individuality or on promoting interdependence. A collectivist culture acknowledges the importance of relationships and presence of social factors in influencing a person's opinion. By contrast, in an individualist culture, self-worth is intrinsic and independence of actions and opinions is valued (Triandis et al [1], Hofstede et al [2]).The aim of our work is to study whether the social behavior of Twitter users reflect the ideologies of the culture they belong to or not. Twitter can be considered as emulating a human society. There are several social factors which play an important role in modeling the user behavior. A user might comment on a general topic trending globally, or might refer to a topic which is being extensively discussed in his local network. Some users prefer tweeting about a topic of their interest, irrespective of the global and local trends, while some are strongly influenced by a subset of their friends.We model the social influence factors as features in our task to predict the content in a user's tweet. We perform a fine-grained analysis by modeling each user network locally. We later apply our model to study the social influence in users of Egypt, India and US. To the best of our knowledge, this is the first work to study the influence of friends in social media in cultures. Our hypothesis was that users of individualistic cultures (e.g US) would not be influenced as much by their friends in predicting their tweeting behavior as users of collectivist cultures (e.g Egypt and India).We study the cultural difference between them by analyzing the weights given by our model to the various factors which help in predicting the user behavior. From the technical standpoint, the paper provides the following contributions.• We define the notion of relatedness between the keywords by using the algorithm described in [28]. The relatedness value captures the degree of co-occurence between the keywords which help in our prediction task.• Most literature on social networks (e.g.[8]) studies the network as a whole to understand large scale global beh...

A Comprehensive Survey of Time Series Anomaly Detection in Online Social Network Data

“…Inviters are somewhat dynamic users who are occupied with articulating their disconnected groups into on the web and efficiently associated with welcoming and urging their companions to join the online services. They are most persuasive users in the way of life of the system [21]. These users with abnormal state of trust to OSNs effortlessly share their own data, cross through the system, and openly disseminate their own points of interest.…”

Language agnostic meme-filtering for hashtag-based social network analysis

“…Sentiment analysis (Kouloumpis et al 2011), event recognition (Valkanas and Gunopulos 2013), trend identification (Parker et al 2013), community recognition (Qi et al 2014), influence propagation (Gupta et al 2013) are just a few characteristic examples.…”