Constructing Semantic Models From Words, Images, and Emojis

Abstract

A number of recent models of semantics combine linguistic information, derived from text corpora, and visual information, derived from image collections, demonstrating that the resulting multimodal models are better than either of their unimodal counterparts, in accounting for behavioural data. Empirical work on semantic processing has shown that emotion also plays an important role especially for abstract concepts, however, models integrating emotion along with linguistic and visual information are lacking. Here, we first improve on visual and affective representations, derived from state-of-the-art existing models, by choosing models that best fit available human semantic data and extending the number of concepts they cover. Crucially then, we assess whether adding affective representations (obtained from a neural network model designed to predict emojis from co-occurring text) improves the model’s ability to fit semantic similarity/relatedness judgements from a purely linguistic and linguistic-visual model. We find that, given specific weights assigned to the models, adding both visual and affective representations improve performance, with visual representations providing an improvement especially for more concrete words, and affective representations improving especially the fit for more abstract words.

Sentiment analysis and its applications in fighting COVID-19 and infectious diseases: A systematic review

“…The previous process was performed to retrieve the most related articles. Despite the availability of other retrieving models, such as cosine similarity, which is considered a measure that has been extensively applied in pattern recognition and text classification to measure how the documents are similar ( Al-Anzi and AbuZeina, 2017 , Aljuaid et al, 2020 ), or other semantic similarity models ( Rotaru & Vigliocco, 2020 ), these models exhibit some limitations, such as data access and inability to apply some search filters ( i.e., publication types, languages, specific data search or search areas ). Thus, the selection of these models was not the best practice in conducting a systematic review.…”