Semantic flow in language networks
This provides a method for analyzing semantic features in texts, potentially enhancing traditional network models that focus only on syntax or style, though it appears incremental in its application to book classification.
The authors tackled the problem of characterizing documents by their semantic flow, using a network-based model to connect sentences by semantic similarity and detect semantic fields with community detection. They achieved 92.5% accuracy in classifying books by style and publication date without systematic parameter optimization.
In this study we propose a framework to characterize documents based on their semantic flow. The proposed framework encompasses a network-based model that connected sentences based on their semantic similarity. Semantic fields are detected using standard community detection methods. as the story unfolds, transitions between semantic fields are represent in Markov networks, which in turned are characterized via network motifs (subgraphs). Here we show that the proposed framework can be used to classify books according to their style and publication dates. Remarkably, even without a systematic optimization of parameters, philosophy and investigative books were discriminated with an accuracy rate of 92.5%. Because this model captures semantic features of texts, it could be used as an additional feature in traditional network-based models of texts that capture only syntactical/stylistic information, as it is the case of word adjacency (co-occurrence) networks.