# A New Approach for Topic Detection using Adaptive Neural Networks

## TL;DR

This paper introduces ClusART, a three-phase topic detection method using lexical preprocessing, vector generation, and a combination of FuzzyART and Paragraph Vector classifiers, demonstrating effectiveness on the 20 Newsgroups dataset.

## Contribution

It presents a novel three-phase approach combining neural network algorithms for improved topic detection in electronic texts.

## Key findings

- Effective detection of relevant topics on 20 Newsgroups dataset
- Combines FuzzyART training with Paragraph Vector classification
- Shows promising results compared to existing methods

## Abstract

Topic detection becomes more important due to the increase of information electronically available and the necessity to process and filter it. In this context our master's thesis work was carried out, where we proposed to present a new approach to the detection of topics called ClusART. Thus, we proposed a three-phase approach, namely : a first phase during which lexical preprocessing was conducted. A second phase during which the construction and generation of vectors representing the documents was carried out. A third phase which is itself composed of two steps. In the first step we used the FuzzyART algorithm for the training phase. In the second step we used a classifier using Paragraph Vector for the test phase. The comparative study of our approach on the 20 Newsgroups dataset showed that our approach is able to detect almost relevant topics.