Temporal Random Indexing: a Tool for Analysing Word Meaning Variations in News

The availability of data spanning different epochs has inspired a new analysis of cultural, social, and linguistic phenomena from a temporal perspective. This paper describes the application of Temporal Random Indexing (TRI) to the news context. TRI is able to build geometrical spaces of word meanings that consider several periods of time. Hence, TRI enables the analysis of the evolution in time of the meaning of a word. We propose some examples of application of TRI to the analysis of word meanings in the news scenario; this analysis enables the detection of linguistic variations that emerge in specific time intervals and that can be related to particular events.

• Type: Journal
• Year: 2016
• Where: ECIR
• Authors: Pierpaolo Basile, Annalina Caputo, Giovanni Semeraro
• Keywords: ECIR 2016, Information Technology