POSLAN: Disentangling Chat with Positional and Language encoded Post Embeddings

TL;DR

This paper introduces POSLAN, an unsupervised method that creates embeddings capturing linguistic and positional features to disentangle cluttered message threads and infer reply relations without relying on platform metadata.

Contribution

It proposes a novel embedding approach combining positional and language features to identify reply relations in message threads without supervision.

Findings

Effective in disentangling cluttered message threads

Works with limited meta data from Telegram

Unsupervised approach successfully infers reply relations

Abstract

Most online message threads inherently will be cluttered and any new user or an existing user visiting after a hiatus will have a difficult time understanding whats being discussed in the thread. Similarly cluttered responses in a message thread makes analyzing the messages a difficult problem. The need for disentangling the clutter is much higher when the platform where the discussion is taking place does not provide functions to retrieve reply relations of the messages. This introduces an interesting problem to which \cite{wang2011learning} phrases as a structural learning problem. We create vector embeddings for posts in a thread so that it captures both linguistic and positional features in relation to a context of where a given message is in. Using these embeddings for posts we compute a similarity based connectivity matrix which then converted into a graph. After employing a pruning mechanisms the resultant graph can be used to discover the reply relation for the posts in the thread. The process of discovering or disentangling chat is kept as an unsupervised mechanism. We present our experimental results on a data set obtained from Telegram with limited meta data.