Grouping Business News Articles using Multiple Objectives Based Particle Swarm Optimization

with the increase in internet use, a large amount of online business news text articles are posting on web portals, social media platforms, and other information-sharing platforms. For any business news platform, it is very crucial for organizing such business news articles for their subscribers, readers, traders, and investors. These business articles are on focused and specific themes like new hiring, funding, IPO, NFO, merger, and acquisitions. These themes may overlap with each other because of similar domain jargon and vocabulary. Efficient segregation of these business articles makes it easier to manage and handle. The clustering algorithm can be useful for grouping and segregating business articles efficiently. These groups and clusters are highly similar within clusters compared to other clusters. Clustering business articles is applicable in web mining, search engine, business news summarization, and information retrieval. In this paper, we are clustering the business news articles scraped from various news portals using various feature engineerings such as BoW, TF-IDF, Part of Speech (PoS) tags, Named Entity Recognition (NER) tags, and Word Embedding such as Word2Vec (CBOW and Skip-gram) and Doc2Vec (PV-DBOW and PV-DM) and grouped the business news articles using Multi-objective Particle Swarm optimization (MOPSO) clustering approach. We have compared the results with available cluster analysis techniques such as K-means, GMM, hierarchical, spectral, and HMM clustering techniques.