# Code Smell Detection using Multilabel Classification Approach

## TL;DR

This paper introduces a multilabel classification approach for detecting multiple code smells simultaneously in source code, addressing the limitations of previous single-label methods and improving detection accuracy.

## Contribution

It proposes a novel multilabel classification method for code smell detection, enabling identification of multiple smells in code elements, which better reflects real-world scenarios.

## Key findings

- Multilabel methods achieved high accuracy in detecting multiple code smells.
- The approach outperformed traditional single-label detection methods.
- Good performance demonstrated through 10-fold cross-validation.

## Abstract

Code smells are characteristics of the software that indicates a code or design problem which can make software hard to understand, evolve, and maintain. The code smell detection tools proposed in the literature produce different results, as smells are informally defined or are subjective in nature. To address the issue of tool subjectivity, machine learning techniques have been proposed which can learn and distinguish the characteristics of smelly and non-smelly source code elements (classes or methods). However, the existing machine learning techniques can only detect a single type of smell in the code element which does not correspond to a real-world scenario. In this paper, we have used multilabel classification methods to detect whether the given code element is affected by multiple smells or not. We have considered two code smell datasets for this work and converted them into a multilabel dataset. In our experimentation, Two multilabel methods performed on the converted dataset which demonstrates good performances in the 10-fold cross-validation, using ten repetitions.