Exploring Temporal Analysis of Tweet Content from Cultural Events - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Exploring Temporal Analysis of Tweet Content from Cultural Events


Online social networking platforms are an important commu- nication medium for cultural events, as they allow exchanging opinions almost in real-time, by publishing messages during the event itself, but also outside of this period. Word embedding has become a popular way to represent and extract information from such messages. In this paper, we propose a preliminary work aiming at assessing the benefits of taking temporal information into account when modeling messages in the context of a cultural event. We perform statistical and visual analyses on two different word representations: one including temporal information (Temporal Embedding), the second ignoring it (Word2Vec approach). Our preliminary results show that the obtained models exhibit some similarities, but also di er signi cantly in the way they represent certain speci c words. More interestingly, the temporal information conveyed by the Temporal Embedding model allows to identify more relevant word associations related to the domain at hand (cultural festivals).
Fichier principal
Vignette du fichier
paper_26.pdf (1.19 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01580578 , version 1 (01-09-2017)


Attribution - NonCommercial - ShareAlike



Mathias Quillot, Cassandre Ollivier, Richard Dufour, Vincent Labatut. Exploring Temporal Analysis of Tweet Content from Cultural Events. 5th International Conference on Statistical Language and Speech Processing (SLSP), 2017, Le Mans, France. pp.82-93, ⟨10.1007/978-3-319-68456-7_7⟩. ⟨hal-01580578⟩


268 View
237 Download



Gmail Facebook Twitter LinkedIn More