Affect Enriched Word Embeddings for News Information Retrieval

TL;DR

This paper explores the use of affect-enriched word embeddings, specifically Aff2Vec, to improve news information retrieval by better capturing emotional nuances and reducing semantic confusion, leading to enhanced query expansion and ranking.

Contribution

It introduces affect-enriched embeddings for news IR, demonstrating their effectiveness over traditional models in capturing emotional context and improving retrieval performance.

Findings

Affect-enriched embeddings outperform traditional models in IR tasks.

They better distinguish emotional content, reducing synonym/antonym confusion.

Improved retrieval results on the NYT dataset.

Abstract

Distributed representations of words have shown to be useful to improve the effectiveness of IR systems in many sub-tasks like query expansion, retrieval and ranking. Algorithms like word2vec, GloVe and others are also key factors in many improvements in different NLP tasks. One common issue with such embedding models is that words like happy and sad appear in similar contexts and hence are wrongly clustered close in the embedding space. In this paper we leverage Aff2Vec, a set of word embeddings models which include affect information, in order to better capture the affect aspect in news text to achieve better results in information retrieval tasks, also such embeddings are less hit by the synonym/antonym issue. We evaluate their effectiveness on two IR related tasks (query expansion and ranking) over the New York Times dataset (TREC-core '17) comparing them against other word embeddings based models and classic ranking models.