Volume - 13 | Issue-1
Volume - 13 | Issue-1
Volume - 13 | Issue-1
Volume - 13 | Issue-1
Volume - 13 | Issue-1
Business Intelligence (BI) and Topic Modelling are two fields that can provide valuable insights to businesses. Latent Dirichlet Allocation (LDA) is a popular technique used for Topic Modelling, but it has some limitations, including the inability to handle unstructured data and lack of interpretability. In this paper, we propose the use of Modified LDA, which incorporates domain-specific knowledge and unstructured data into the Topic Modelling process to address some of the research gaps in the application of BI and Topic Modelling. We evaluate the performance of Modified LDA using a real-world dataset and compare it with other Topic Modelling techniques. Our results show that Modified LDA outperforms other techniques in terms of accuracy and interpretability. Our study has implications for businesses looking to integrate structured and unstructured data and provide more comprehensive insights.