Show me the material evidence: Initial experiments on evaluating hypotheses from user-generated multimedia data

TL;DR

This paper explores initial experiments on evaluating hypotheses using user-generated multimedia data as material evidence, aiming to support collective decision-making in cognitive computing systems.

Contribution

It introduces preliminary experiments on leveraging multimedia evidence from social media to evaluate subjective hypotheses, highlighting challenges in evidence collection and aggregation.

Findings

Initial experiments demonstrate feasibility of multimedia evidence collection.

Challenges include data heterogeneity and evidence reliability.

Potential for supporting collective decision-making in cognitive systems.

Abstract

Subjective questions such as `does neymar dive', or `is clinton lying', or `is trump a fascist', are popular queries to web search engines, as can be seen by autocompletion suggestions on Google, Yahoo and Bing. In the era of cognitive computing, beyond search, they could be handled as hypotheses issued for evaluation. Our vision is to leverage on unstructured data and metadata of the rich user-generated multimedia that is often shared as material evidence in favor or against hypotheses in social media platforms. In this paper we present two preliminary experiments along those lines and discuss challenges for a cognitive computing system that collects material evidence from user-generated multimedia towards aggregating it into some form of collective decision on the hypothesis.