Trends Prediction Using Social Diffusion Models

Abstract

Abstract. The importance of the ability to predict trends in social media has been growing rapidly in the past few years with the growing dominance of social media in our everyday's life. Whereas many works focus on the detection of anomalies in networks, there exist little theoretical work on the prediction of the likelihood of anomalous network pattern to globally spread and become "trends". In this work we present an analytic model for the social diffusion dynamics of spreading network patterns. Our proposed method is based on information diffusion models, and is capable of predicting future trends based on the analysis of past social interactions between the community's members. We present an analytic lower bound for the probability that emerging trends would successfully spread through the network. We demonstrate our model using two comprehensive social datasets -the Friends and Family experiment that was held in MIT for over a year, where the complete activity of 140 users was analyzed, and a financial dataset containing the complete activities of over 1.5 million members of the eToro social trading community.

Predicting Adoption Probabilities in Social Networks

“…This is intriguing because previous research shows the important effects of social influence , Altshuler et al 2012, Pickard et al 2011, while pointing out the significance of other forces. Forces above and beyond social influence are also recognized by (Bakshy et al 2011, Watts andPeretti 2007), congruent with our approach.…”

“…By summing adoption probabilities across potential adopters, a firm could predict the expected number of adopters in the next time period. Such prediction allows firms to gauge whether an offering is likely to go viral, which has crucial implications for their business decisions (Altshuler et al 2012, Bandari et al 2012). For example, if an offering is likely to go viral, the firm could act proactively to leverage the anticipated viral with appropriate marketing strategies, such as bundling or cross-selling.…”

Improving trend analysis using social network features

“…For this, it is necessary to identify these groups or communities, which is not a trivial task [16]. Another challenge is to identify critical points in the network where the probability of information diffusion increases [2]. Finally, social network information is being used in several ways to predict trends based on the network behavior [13].…”

Detecting Anomalous Behaviors Using Structural Properties of Social Networks

“…These techniques can be used to detect social relations [1,13], evolving behavioral trends [7,24], mobility patterns [15], environmental hazards [18,25], socio-economical properties [14], and various security related features [4,5].…”