Multiclass Text Classification Using Deep Learning
DOI:
https://doi.org/10.63282/3050-922X.ICAILLMBA-122Keywords:
Deep Learning, Long Short-Term Memory (Lstm), Natural Language Processing, News Article Classification, Bbc Text Dataset, Tf-Idf, Word Embeddings, Sequence Modeling, InformationAbstract
The exponential growth of digital news content has created a critical need for automated techniques that can efficiently organize and categorize textual information. Multiclass text classification plays a vital role in structuring large-scale news articles by assigning them to predefined thematic categories. This study proposes a deep learning–driven framework for the multiclass categorization of news articles using the BBC Text Dataset. The approach incorporates essential natural language processing steps, including text tokenization, removal of stop words, stemming, and lemmatization, to clean and standardize the input data. Textual features are represented using both TF-IDF and word embedding methods to effectively capture semantic information. An LSTM-based neural network is utilized to model the sequential nature and contextual relationships within the text. The model’s performance is evaluated using widely accepted metrics such as accuracy, precision, recall, and F1-score. The experimental findings indicate that the proposed method attains an average classification accuracy of about 91%, demonstrating superior performance compared to conventional machine learning techniques. The study highlights the effectiveness of LSTM-based architectures for automated news categorization and demonstrates their potential for real-world content management and information retrieval systems.
References
[1] A. McCallum and K. Nigam, “A comparison of event models for naive Bayes text classification,” Proc. AAAI Workshop on Learning for Text Categorization, Madison, WI, USA, 1998, pp. 41–48.
[2] Cortes, C.,& Vapnak, V.(1995). Support Vector Networks. Machine Learning, 20(3), 273-297
[3] R. Collobert, J. Weston, L. Bottou, M. Karlen, K. Kavukcuoglu, and P. Kuksa, “Natural language processing (almost) from scratch,” J. Mach. Learn. Res., vol. 12, pp. 2493–2537, 2011.
[4] A. Graves, S. Fernández, J. Schmidhuber, and P. Frasconi, “Bidirectional LSTM networks for improved phoneme classification and recognition,” in Proc. Int. Conf. Artificial Neural Networks (ICANN), 2013, pp. 277–284.
[5] Y. Yang and J. O. Pedersen, “A comparative study on feature selection in text classification,” in Proc. 14th Int. Conf. Machine Learning (ICML), 1997, pp. 412–420.
[6] X. Zhang and B. C. Wallace, “A sensitivity analysis of (and practitioner’s guide to) convolutional neural networks for sentence classification,” in Proc. 2015 Conf. Empirical Methods in Natural Language Processing (EMNLP), 2015, pp. 253–263.
[7] Y. Zhang, X. Zhao, and H. Liu, “Hybrid convolutional and recurrent neural networks for text classification,” in Proc. 33rd Conf. Neural Information Processing Systems (NeurIPS), 2019, pp. 4541–4551.
[8] Y. Kim, “Convolutional neural networks for sentence classification,” in Proc. 2014 Conf. Empirical Methods in Natural Language Processing (EMNLP), 2014, pp. 1746–1751.
[9] J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. 2018 Conf. North American Chapter of the Assoc. for Computational Linguistics (NAACL), 2018, pp. 4171–4186.
[10] R. Johnson and T. Zhang, “Effective use of word order for text classification with convolutional neural networks,” in Proc. 2015 Conf. Empirical Methods in Natural Language Processing (EMNLP), 2015, pp. 103–112.
[11] M. Yu and X. Hu, “Multi-channel attention-based convolutional neural networks for text classification,” in Proc. 2020 Conf. Empirical Methods in Natural Language Processing (EMNLP), 2020, pp. 4062–4070.
[12] Z. Lin, A. Yang, and R. Socher, “A structured self-attentive sentence embedding,” in Proc. Int. Conf. Learning Representations (ICLR), 2017, pp. 1–10.
[13] C. Sun, H. Xu, and Z. Yang, “ERNIE: Enhanced representation through knowledge integration,” in Proc. 57th Annu. Meeting Assoc. for Computational Linguistics (ACL), 2019, pp. 1444–1454.
[14] S. Wang and J. Jiang, “A compare-and-contrast study of deep learning models for text classification,” in Proc. 2016 Conf. Empirical Methods in Natural Language Processing (EMNLP), 2016, pp. 1115–1123.
[15] J. Howard and S. Ruder, “Universal language model fine-tuning for text classification,” in Proc. 56th Annu. Meeting Assoc. for Computational Linguistics (ACL), 2018, pp. 328–339.
