Classifying multi-level product categories using dynamic masking and transformer models
Authors:
- 1 March 2022
- journal article
- research article
- Published by Springer Nature in Journal of Data, Information and Management
- Vol. 4 (1) , 71-85
Abstract
In an online shopping platform, a detailed categorization of the products greatly enhances user navigation. Online retailers also benefit from well-defined product categories as various sales and marketing operations such as special discounts and promotions can be easily done over a set of product categories. Furthermore, incorrect and subjective product categories suggested by an operator can be more easily identified thanks to an automated classification system. In this study, we investigate the task of classifying grocery product categories using product titles. We employ a wide variety of text classification models for this task, including traditional machine learning and deep learning models as well as state-of-the-art transformer models. In our analysis, we specifically focus on the generalizability of the trained classification models to the products of other online retailers, the dynamic masking of infeasible subcategories for pretrained language models, and the impact of incorporating different word embeddings. We observe that the deep learning models and the transformers significantly outperform traditional text classification methods such as XGBoost and SVM, and achieve excellent prediction performance exceeding 90% accuracy and F1-score values. We lastly explore the failure cases where a product is misclassified, and make recommendations for future studies to improve the prediction performance.Keywords
This publication has 12 references indexed in Scilit:
- Incorporating context-relevant concepts into convolutional neural networks for short text classificationNeurocomputing, 2020
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks2019
- An analysis of hierarchical text classification using word embeddingsInformation Sciences, 2019
- News Text Classification Based on Improved Bi-LSTM-CNN2018
- Influence of Word Normalization and Chi-Squared Feature Selection on Support Vector Machine (SVM) Text Classification2018
- Improving Medical Short Text Classification with Semantic Expansion Using Word-Cluster Embedding2018
- Research on Web text classification algorithm based on improved CNN and SVM2017
- Combining Knowledge with Deep Convolutional Neural Networks for Short Text Classification2017
- A Novel Active Learning Method Using SVM for Text ClassificationInternational Journal of Automation and Computing, 2016
- Glove: Global Vectors for Word Representation2014