Abstract
Text classification models have been heavily utilized for a slew of interesting natural language processing problems. Like any other machine learning model, these classifiers are very dependent on the size and quality of the training dataset. Insufficient and imbalanced datasets will lead to poor performance. An interesting solution to poor datasets is to take advantage of the world knowledge in the form of knowledge graphs to improve our training data. In this paper, we use ConceptNet and Wikidata to improve sexist tweet classification by two methods (1) text augmentation and (2) text generation. In our text generation approach, we generate new tweets by replacing words using data acquired from ConceptNet relations in order to increase the size of our training set, this method is very helpful with frustratingly small datasets, preserves the label and increases diversity. In our text augmentation approach, the number of tweets remains the same but their words are augmented (concatenation) with words extracted from their ConceptNet relations and their description extracted from Wikidata. In our text augmentation approach, the number of tweets in each class remains the same but the range of each tweet increases. Our experiments show that our approach improves sexist tweet classification significantly in our entire machine learning models. Our approach can be readily applied to any other small dataset size like hate speech or abusive language and text classification problem using any machine learning model.
Highlights
When it comes to machine learning algorithms, the dataset plays a pivotal role in the usability of those models
We considered Support vector Machines (SVM) and Naive Bayes (NB) as the traditional methods and Long-short-term-memory (LSTM) and Convolutional Neural network (CNN) for the choice of deep learning methods (Björn Gambäck and Utpal Kumar Sikdar. 2017 )
The third classification experiment, noun replacement (NR), was on the four balanced datasets coming from the second method of text generation, each class having about one thousand data points and the last experiment coming from the third approach for text generation; each class having the same number of tweets
Summary
When it comes to machine learning algorithms, the dataset plays a pivotal role in the usability of those models. There are many problems where datasets are imbalanced, data is rare or data is hard to collect, hard to label or the overlap between the classes is high. Text generation has been used widely for machine translation, summarization and dialogue generation (Sathish Indurthi et al, 2017) and (Uchimoto, K. et al 2002). One way of understanding these concepts and getting more information about them is by using linked data and knowledge graphs. The popularity of the internet and advancements in linked data research has led to the development of internetscale public domain knowledge graphs such as FreeBase, DBPedia, ConceptNet and Wikidata
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.