Beyond Word Embeddings: Temporal Representations of Words using Google Trends

The main essence of word representation in a vector space is to preserve the similarity between the words. Traditional measures of word similarity retain the contextual or semantic affinity among the words. In this study, we propose an alternative word embedding scheme which considers the temporal relationships among the words. We employ the Google Trends search queries along with the respective time series information to represent words in a vector space. Our experiments show that the proposed representation is capable of incorporating temporal context that is otherwise unavailable in conventional word representations.