Detecting partnership in location-based and online social networks

Abstract

Existing approaches to identify the tie strength between users involve typically only one type of network. To date, no studies exist that investigate the intensity of social relations and in particular partnership between users across social networks. To fill this gap in the literature, we studied over 50 social proximity features to detect the tie strength of users defined as partnership in two different types of networks: location-based and online social networks. We compared user pairs in terms of partners and non-partners and found significant differences between those users. Following these observations, we evaluated the social proximity of users via supervised and unsupervised learning approaches and establish that location-based social networks have a great potential for the identification of a partner relationship. In particular, we established that location-based social networks and correspondingly induced features based on events attended by users could identify partnership with 0.922 AUC, while online social network data had a classification power of 0.892 AUC. When utilizing data from both types of networks, a partnership could be identified to a great extent with 0.946 AUC. This article is relevant for engineers, researchers and teachers who are interested in social network analysis and mining.

Evaluating the importance of different communication types in romantic tie prediction on social media

“…This can be explained by the theory of homophily:'birds of a feather flock together' (McPherson et al, 2001). Hence, people who are more alike and share common interests, have a higher chance of being in a relationship (Trattner and Steurer, 2015).…”

“…First, our study is limited since we do not include features related to the whole social network (i.e., topological features) in our analysis. Nevertheless, these variables have proven to be successful in predicting romantic relationships (Backstrom and Kleinberg, 2014;Trattner and Steurer, 2015).…”

Recommending Sellers to Buyers in Virtual Marketplaces Leveraging Social Information

“…Using social information to provide or improve recommenders is a relatively new strand of research. Most notable work in this direction has been performed recently in the context of, for instance, recommending points-of-interest to people (e.g., [8]), recommending tags to people (e.g., [10]), or predicting social interactions (e.g., [4,19]) or relations (e.g., [22]).…”

“…At the end of March 2013 we crawled the SL profiles of users who had not changed their profiles to private, based on the crawling methodology as described in our previous work [22]. For each user we obtained the stated interests, the joined groups, the feed interactions with others (text messages, pictures, comments, likes) and the preferred in-world locations-so-called favored regions.…”