# Semantic flow in language networks

## TL;DR

This paper introduces a network-based framework to analyze the semantic flow in texts, enabling classification of books by style and date with high accuracy, and capturing semantic features beyond traditional syntactic models.

## Contribution

The study presents a novel semantic flow network model that detects semantic fields and transitions, improving text classification and understanding of semantic dynamics in documents.

## Key findings

- Achieved 92.5% accuracy in classifying books by style and publication date.
- Demonstrated the framework's ability to distinguish philosophical and investigative texts.
- Showed the model captures semantic features beyond syntactic analysis.

## Abstract

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.