Interactive Search and Exploration in Online Discussion Forums Using Multimodal Embeddings

TL;DR

This paper introduces a novel interactive multimodal learning system for search and exploration in online social multimedia networks, leveraging neural embeddings of users, words, and concepts to improve user profiling and content summarization.

Contribution

The paper proposes a new neural embedding approach for multimodal user representations, enabling interactive search, user profiling, and content summarization in large social multimedia networks.

Findings

Multimodal representations effectively categorize users and generate profiles.

The approach improves search and exploration in social multimedia platforms.

Experiments demonstrate the utility on Stormfront and Twitter datasets.

Abstract

In this paper we present a novel interactive multimodal learning system, which facilitates search and exploration in large networks of social multimedia users. It allows the analyst to identify and select users of interest, and to find similar users in an interactive learning setting. Our approach is based on novel multimodal representations of users, words and concepts, which we simultaneously learn by deploying a general-purpose neural embedding model. We show these representations to be useful not only for categorizing users, but also for automatically generating user and community profiles. Inspired by traditional summarization approaches, we create the profiles by selecting diverse and representative content from all available modalities, i.e. the text, image and user modality. The usefulness of the approach is evaluated using artificial actors, which simulate user behavior in a relevance feedback scenario. Multiple experiments were conducted in order to evaluate the quality of our multimodal representations, to compare different embedding strategies, and to determine the importance of different modalities. We demonstrate the capabilities of the proposed approach on two different multimedia collections originating from the violent online extremism forum Stormfront and the microblogging platform Twitter, which are particularly interesting due to the high semantic level of the discussions they feature.