Economic and financial news hybrid- classification based on category-associated feature set

Abstract

A large amount of economic and financial news is now accessible through various news websites and social media platforms. Categorizing them into appropriate categories can be advantageous for various tasks, such as sentiment analysis and news-based market prediction. Unfortunately, news headlines categories may contain ambiguities due to the subjective nature of label assignment by authors or publishers. Consequently, achieving precise classification of news can be time-consuming and still reliant on human expertise. To tackle this challenging task, we proposed a hybrid approach to enhance the performance of economic and financial news classification. This approach combines baseline classifiers with a novel method called the Category Associated Feature Set (CAFS) classifier. CAFS transforms text input from the lexicon-space into the entity-space and discovers associations between entities and classes, akin to association rule learning. Experimental results on three datasets demonstrated that the proposed method is comparable to existing approaches and exhibits a significant improvement in the classification results for out-of-domain datasets. Additionally, employing CAFS in tandem with the existing text classification baselines can provide a general categorizer for distinguishing news categories across various sources without the need for extensive fine-tuning of the parameters associated with those classification baselines. This confirms that utilizing CAFS in a hybrid approach is appropriate and suitable for economic and financial news classification.