Linking Tweets with Monolingual and Cross-Lingual News using Transformed Word Embeddings

TL;DR

This paper introduces a transformation framework that aligns word embeddings from tweets and news articles across languages, improving the ability to link social media content with traditional news sources.

Contribution

The novel framework effectively bridges the word usage gap between informal tweets and formal news articles across languages using transformed word embeddings.

Findings

Improved matching accuracy for monolingual tweets and news articles.

Enhanced cross-lingual comparison capabilities.

Significant performance gains over baseline methods.

Abstract

Social media platforms have grown into an important medium to spread information about an event published by the traditional media, such as news articles. Grouping such diverse sources of information that discuss the same topic in varied perspectives provide new insights. But the gap in word usage between informal social media content such as tweets and diligently written content (e.g. news articles) make such assembling difficult. In this paper, we propose a transformation framework to bridge the word usage gap between tweets and online news articles across languages by leveraging their word embeddings. Using our framework, word embeddings extracted from tweets and news articles are aligned closer to each other across languages, thus facilitating the identification of similarity between news articles and tweets. Experimental results show a notable improvement over baselines for monolingual tweets and news articles comparison, while new findings are reported for cross-lingual comparison.