Tracking the Evolution of Words with Time-reflective Text Representations

More than 80% of today's data is unstructured in nature, and these unstructured datasets evolve over time. A large part of these datasets are text documents generated by media outlets, scholarly articles in digital libraries, findings from scientific and professional communities, and social media. Vector space models were developed to analyze text data using data mining and machine learning algorithms. While ample vector space models exist for text data, the evolutionary aspect of ever-changing text corpora is still missing in vector-based representations. The advent of word embeddings has enabled us to create a contextual vector space, but the embeddings fail to consider the temporal aspects of the feature space successfully. This paper presents an approach to include temporal aspects in feature spaces. The inclusion of the time aspect in the feature space provides vectors for every natural language element, such as words or entities, at every timestamp. Such temporal word vectors allow us to track how the meaning of a word changes over time, by studying the changes in its neighborhood. Moreover, a time-reflective text representation will pave the way to a new set of text analytic abilities involving time series for text collections. In this paper, we present a time-reflective vector space model for temporal text data that is able to capture short and long-term changes in the meaning of words. We compare our approach with the limited literature on dynamic embeddings. We present qualitative and quantitative evaluations using the tracking of semantic evolution as the target application.