Classifying movie genres by analyzing text reviews

TL;DR

This study explores classifying movie genres solely based on text reviews using KNN and MLP models, highlighting the effectiveness of KNN with a 55.4% accuracy in multi-label genre classification.

Contribution

It compares KNN and MLP models for genre classification from reviews and discusses evaluation metrics for multi-label classification.

Findings

KNN outperformed MLP with 55.4% accuracy

KNN achieved a Hamming loss of 0.047

Evaluation metrics for multi-label classification are discussed

Abstract

This paper proposes a method for classifying movie genres by only looking at text reviews. The data used are from Large Movie Review Dataset v1.0 and IMDb. This paper compared a K-nearest neighbors (KNN) model and a multilayer perceptron (MLP) that uses tf-idf as input features. The paper also discusses different evaluation metrics used when doing multi-label classification. For the data used in this research, the KNN model performed the best with an accuracy of 55.4\% and a Hamming loss of 0.047.