Wednesday, August 12, 2026 Strategy, technology, media, and social systems

I Think

Sorin Adam Matei

Analysis, research, maps, and essays from Sorin Adam Matei.

How to derive social networks from web forum, chat, or other time based asynchronous communication data and conversation threads

An excerpt from the chart as of season four, s...
Social Network Structure Image via Wikipedia

Vehovar Vasja and Ziberna Alesia, the first mentioned previously on this blog for his work on recommending systems,  proposes this method for deriving social networking data from conversation threads:

Abstract of Measuring ties on online forums Ziberna and Vehovar, 7th International Conference on Social Science Methodology, 2008 & Applied Statistics 2008

In this paper we discus analysis of social networks among participants of online forums (or online discussion boards). We focus on usual type of online forums where there is only almost no direct information about which post a given post responds to. Usually, all information we have about a most is it’s author, time of post and the thread in which it was posted. There exists some ”direct information” on ties between authors, the citations, but they are relatively rarely used in on-line forums. We will however argue that we can still infer connections between authors based on their posts.

In the paper we discuss assumptions that allow us to infer ties between authors without using direct information and the networks that we obtain using them. We discuss three options for defining a tie. Two persons/users are in a tie if:

1. posts reply to k posts before them in a given thread (topic). Of course, the probability that a post replies to some previous posts decreases by the distance in time and number of posts between them (i.e. k)

2. all posts reply are in tie only the first post in the thread (topic).

3. all persons in a certain thread (topic) are in a tie.

We will also test our approach on an empirical forum and enforce our argument that ties can be inferred without direct information by the similarity of the obtained networks with the citation network on a subset of authors that uses them the most. We will also show some possible uses of networks obtained in such manner.

Reblog this post [with Zemanta]

Join the discussion

Your email address will not be published. Required fields are marked *