Social relation | EPFL Graph Search

A social relation is the fundamental unit of analysis within the social sciences, and describes any voluntary or involuntary interpersonal relationship between two or more individuals within and/or between groups. The group can be a language or kinship group, a social institution or organization, an economic class, a nation, or gender. Social relations are derived from human behavioral ecology, and, as an aggregate, form a coherent social structure whose constituent parts are best understood relative to each other and to the social ecosystem as a whole. History Early inquiries into the nature of social relations featured in the work of sociologists such as Max Weber in his theory of social action, where social relationships composed of both positive (affiliative) and negative (agonistic) interactions represented opposing effects. Categorizing social interactions enables observational and other social research, such as Gemeinschaft and Gesellschaft (lit. 'community and soc

AntispamLab - A Tool for Realistic Evaluation of Email Spam Filters

Luis Hernandez, Jean-Yves Le Boudec, Raphaël Naefen, Slavisa Sarafijanovic

The existing tools for testing spam filters evaluate a filter instance by simply feeding it with a stream of emails, possibly also providing a feedback to the filter about the correctness of the detection. In such a scenario the evaluated filter is disconnected from the network of email servers, filters, and users, which makes the approach inappropriate for testing many of the filters that exploit some of the information about spam bulkiness, users' actions and social relations among the users. Corresponding evaluation results might be wrong, because the information that is normally used by the filter is missing, incomplete or inappropriate. In this paper we present a tool for testing spam filters in a very realistic scenario. Our tool consists of a set of Python scripts for unix/linux environment. The tool takes as inputs the filter to be tested and an affordable set of interconnected machines (e.g., PlanetLab machines, or locally created virtual machines). When started from a central place, the tool uses the provided machines to build a network of real email servers, installs instances of the filter, deploys and runs simulated email users and spammers, and computes the detection results statistic. Email servers are implemented using Postfix, a standard linux email server. Only per-email-server filters are currently supported, whereas per-email-client filters testing would require additional tool development. The size of the created emailing network is constrained only by the number of available PlanetLab or virtual machines. The run time is much shorter then the simulated system time, due to a time scaling mechanism. Testing a new filter is as simple as installing one copy of it in a real emailing network, which unifies the jobs of a new filter development, testing and prototyping. As a usage example, we test the SpamAssassin filter.

2007

Social Network Analysis in Multimedia Indexing: Making Sense of People in Multiparty Recordings

Sarah Favre

This paper presents an automatic approach to analyze the human interactions appearing in multiparty data, aiming at understanding the data content and at extracting social informa- tion such as Which role do people play?, What is their attitude?, or Can people be split into meaningful groups?. To extract such information, we use a set of mathematical techniques, namely Social Networks Analysis (SNA), developed by sociologists to analyze social interac- tions. This paper shows that a strong connection can be established between the content of broadcast data and the social interactions of the individuals involved in the recordings. Experiments aiming at assigning each individual to a social group corresponding to a specific topic in broadcast news, and experiments aiming at recognizing the role played by each indi- vidual in multiparty data are presented in this paper. The results achieved are satisfactory, which suggests on one side that the application of SNA to similar problems could lead to useful contributions in the domain of multimedia content analysis, and on the other side, that the presented analysis of social interactions could be a significant breakthrough for affective computing.

2009

Social Network Analysis for Automatic Role Recognition

Sarah Favre

The computing community has shown a significant interest for the analysis of social interactions in the last decade. Different aspects of social interactions have been studied such as dominance, emotions, conflicts, etc. However, the recognition of roles has been neglected whereas these are a key aspect of social interactions. In fact, sociologists have shown not only that people play roles each time they interact, but also that roles shape behavior and expectations of interacting participants. The aim of this thesis is to fill this gap by investigating the problem of automatic role recognition in a wide range of interaction settings, including production environments, e.g. news and talk-shows, and spontaneous exchanges, e.g. meetings. The proposed role recognition approach includes two main steps. The first step aims at representing the individuals involved in an interaction with feature vectors accounting for their relationships with others. This step includes three main stages, namely segmentation of audio into turns (i.e. time intervals during which only one person talks), conversion of the sequence of turns into a social network, and use of the social network as a tool to extract features for each person. The second step uses machine learning methods to map the feature vectors into roles. The experiments have been carried out over roughly 90 hours of material. This is not only one of the largest databases ever used in literature on role recognition, but also the only one, to the best of our knowledge, including different interaction settings. In the experiments, the accuracy of the percentage of data correctly labeled in terms of roles is roughly 80% in production environments and 70% in spontaneous exchanges (lexical features have been added in the latter case). The importance of roles has been assessed in an application scenario as well. In particular, the thesis shows that roles help to segment talk-shows into stories, i.e. time intervals during which a single topic is discussed, with satisfactory performance. The main contributions of this thesis are as follows: To the best of our knowledge, this is the first work where social network analysis is applied to automatic analysis of conversation recordings. This thesis provides the first quantitative measure of how much roles constrain conversations, and a large corpus of recordings annotated in terms of roles. The results of this work have been published in one journal paper, and in five conference articles.

EPFL2011

Social Network Analysis for Automatic Role Recognition

Sarah Favre

EPFL2011

AntispamLab - A Tool for Realistic Evaluation of Email Spam Filters

Luis Hernandez, Jean-Yves Le Boudec, Raphaël Naefen, Slavisa Sarafijanovic

2007