MCNN-LSTM: Combining CNN and LSTM to Classify Multi-Class Text in Imbalanced News Data

Abstract

Searching, retrieving, and arranging text in ever-larger document collections necessitate more efficient information processing algorithms. Document categorization is a crucial component of various information processing systems for supervised learning. As the quantity of documents grows, the performance of classic supervised classifiers has deteriorated because of the number of document categories. Assigning documents to a predetermined set of classes is called text classification. It is utilized extensively in a wide range of data-intensive applications. However, the fact that real-world implementations of these models are plagued with shortcomings begs for more investigation. Imbalanced datasets hinder the most prevalent high-performance algorithms. In this paper, we propose an approach name multi-class Convolutional Neural Network (MCNN)-Long Short-Time Memory (LSTM), which combines two deep learning techniques, Convolutional Neural Network (CNN) and Long Short-Time Memory, for text classification in news data. CNN's are used as feature extractors for the LSTMs on text input data and have the spatial structure of words in a sentence, paragraph, or document. The dataset is also imbalanced, and we use the Tomek-Link algorithm to balance the dataset and then apply our model, which shows better performance in terms of F1-score (98%) and Accuracy (99.71%) than the existing works. The combination of deep learning techniques used in our approach is ideal for the classification of imbalanced datasets with underrepresented categories. Hence, our method outperformed other machine learning algorithms in text classification by a large margin. We also compare our results with traditional machine learning algorithms in terms of imbalanced and balanced datasets.

GreenRu: A Russian Dataset for Detecting Mentions of Green Practices in Social Media Posts

“…The methods of handling imbalanced data can be divided into algorithmic-level and data-level methods [41]. Algorithmic-level methods focus on designing new classification algorithms or enhancing existing ones (for example, [42][43][44]), while data-level methods attempt to balance the data by reducing the majority class or expanding the minority class.…”

Data oversampling and imbalanced datasets: an investigation of performance for machine learning and feature engineering

“…Data balancing is an important task to reduce model skewness and as such several works have made use of oversampling approaches to reduce model overfitting and increase performance [7][8][9]. Sarakit et al [10] employed the SMOTE method to detect emotion in unbalanced YouTube datasets using three machine learning classifiers.…”

Embeddings at BLP-2023 Task 2: Optimizing Fine-Tuned Transformers with Cost-Sensitive Learning for Multiclass Sentiment Analysis

“…Their approach utilizes a range of machine learning and deep learning models, with BERT reaching a maximum accuracy of 99.04% in balanced datasets and 72.23% in imbalanced datasets. Another noteworthy contribution by (Hasib et al, 2023a) introduces MCNN-LSTM, a novel fusion of CNN and LSTM for news text classification. After balancing the dataset using the Tomek-Link algorithm, their model attains remarkable performance, achieving a 98% F1-score and 99.71% accuracy compared to prior research.…”