Keep Your Friends Close, and Your Enemies Closer: Structural Properties of Negative Relationships on Twitter

TL;DR

This paper extends the Ego Network Model to signed networks by introducing a psychology-grounded, data-efficient method to sign Ego–Alter relationships from text interactions on Twitter. It combines sentiment-based signing with Structural Balance Theory validation and constructs Signed Ego Networks across 9 datasets encompassing specialised and generic users. Key findings show that negative relationships are disproportionately represented in active networks, especially among specialised users, and that negativity concentrates in the innermost circles, with only weak evidence of cognitive costs associated with negativity. The work demonstrates robust cross-model stability of signs and provides a reproducible SENM framework, offering insights into online social dynamics and informing diffusion and community analyses on OSNs.

Abstract

The Ego Network Model (ENM) is a model for the structural organisation of relationships, rooted in evolutionary anthropology, that is found ubiquitously in social contexts. It takes the perspective of a single user (Ego) and organises their contacts (Alters) into a series of (typically 5) concentric circles of decreasing intimacy and increasing size. Alters are sorted based on their tie strength to the Ego, however, this is difficult to measure directly. Traditionally, the interaction frequency has been used as a proxy but this misses the qualitative aspects of connections, such as signs (i.e. polarity), which have been shown to provide extremely useful information. However, the sign of an online social relationship is usually an implicit piece of information, which needs to be estimated by interaction data from Online Social Networks (OSNs), making sign prediction in OSNs a research challenge in and of itself. This work aims to bring the ENM into the signed networks domain by investigating the interplay of signed connections with the ENM. This paper delivers 2 main contributions. Firstly, a new and data-efficient method of signing relationships between individuals using sentiment analysis and, secondly, we provide an in-depth look at the properties of Signed Ego Networks (SENs), using 9 Twitter datasets of various categories of users. We find that negative connections are generally over-represented in the active part of the Ego Networks, suggesting that Twitter greatly over-emphasises negative relationships with respect to "offline" social networks. Further, users who use social networks for professional reasons have an even greater share of negative connections.

Figures (23)

• Figure 1: The Ego Network Model, with the names and expected sizes of each subgroup for social networks of humans.
• Figure 2: All four possible signed triads, as per Structural Balance Theory. The subscript number following the “T" corresponds to the number of positive connections for that triad.
• Figure 3: Percentages of positive, neutral and negative interaction labels estimated by each model (95% confidence intervals)
• Figure 4: Percentages of positive and negative relationship labels estimated by each model (95% confidence intervals)
• Figure 5: Example disagreement scatter plot. Each point corresponds to a relationship where two target models (here, VADER and BERTweet) disagree. The x-coordinate of the point corresponds to the percentage of negative interactions in the relationship according to VADER, and the y-coordinate to the percentage of negative interactions in the relationship according to BERTweet. Only relationships with at least 6 interactions are included.