Modeling reciprocity in social interactions with probabilistic latent space models

Abstract

Reciprocity is a pervasive concept that plays an important role in governing people's behavior, judgments, and thus their social interactions. In this paper we present an analysis of the concept of reciprocity as expressed in English and a way to model it. At a larger structural level the reciprocity model will induce representations and clusters of relations between interpersonal verbs. In particular, we introduce an algorithm that semi-automatically discovers patterns encoding reciprocity based on a set of simple yet effective pronoun templates. Using the most frequently occurring patterns we queried the web and extracted 13,443 reciprocal instances, which represent a broad-coverage resource. Unsupervised clustering procedures are performed to generate meaningful semantic clusters of reciprocal instances. We also present several extensions (along with observations) to these models that incorporate metaattributes like the verbs' affective value, identify gender differences between participants, consider the textual context of the instances, and automatically discover verbs with certain presuppositions. The pattern discovery procedure yields an accuracy of 97 per cent, while the clustering procedures -clustering with pairwise membership and clustering with transitionsindicate accuracies of 91 per cent and 64 per cent, respectively. Our affective value clustering can predict an unknown verb's affective value (positive, negative, or neutral) with 51 per cent accuracy, while it can discriminate between positive and negative values with 68 per cent accuracy. The presupposition discovery procedure yields an accuracy of 97 per cent.

Peer-To-Peer Interactions in the Sharing Economy: Exploring the Role of Reciprocity within a Chinese Social Network

“…These different perspectives on reciprocity share common attributes: (1) a relationship of mutual dependence; (2) mutual exchange of benefits; (3) mutual interaction; and (4) the sequential nature of reciprocal actions. Girju and Paul (2011) distinguish between concurrent reciprocity (e.g., two people interacting and simultaneously “liking” each other's posts) and return reciprocity, when one's action directly causes another's reaction (e.g., one person follows another because s/he was kind). Return reciprocity has been frequently observed in sharing economy reputation rating systems (e.g., Arcidiacono, 2018).…”

Learning the Peculiar Value of Actions

“…In natural language processing, there has been very little work on the concept of value. Paul et al (2009) and Girju and Paul (2011) address the problem of semi-automatically mining patterns that encode reciprocal relationships using pronoun templates. Their work focuses on mining patterns of reciprocity while our work uses expressions of reciprocal actions to learn the value of actions.…”