Topic modelling is a prominent task for automatic topic extraction in many applications such as sentiment analysis and recommendation systems. The approach is vital for service industries to monitor their customer discussions. The use of traditional approaches such as Latent Dirichlet Allocation (LDA) for topic discovery has shown great performances, however, they are not consistent in their results as these approaches suffer from data sparseness and inability to model the word order in a document. Thus, this study presents the use of Kernel Principal Component Analysis (KernelPCA) and K-means Clustering in the BERTopic architecture. We have prepared a new dataset using tweets from customers of Nigerian banks and we use this to compare the topic modelling approaches. Our findings showed KernelPCA and K-means in the BERTopic architecture-produced coherent topics with a coherence score of 0.8463.

In this article, we use a genetic algorithm to evolve seven different types of Lucene search query with the objective of generating accurate and readable text classifiers. We compare the effectiveness of each of the different types of query using three commonly used text datasets. We vary the number of words available for classification and compare results for 4, 8 and 16 words per category. The generated queries can also be viewed as labels for the categories and there is a benefit to a human analyst in being able to read and tune the classifier. The evolved queries also provide an explanation of the classification process. We consider the consistency of the classifiers and compare their performance on categories of different complexities. Finally, various approaches to the analysis of the results are briefly explored.

See http://shura.shu.ac.uk/information.html Sheffield Hallam University Research Archive http://shura.shu.ac.uk if hemiplegia then stroke risk 59.0% else if cerebrovascular disorder then stroke risk 44.7% else if hypovolaemia and chest pain then stroke risk 14.6% else if transient ischaemic attack then stroke risk 29.9% else if age_70 then stroke risk 4.5% else stroke risk 9.0%

Document analysis is a well matured yet still active research field, partly as a result of the intricate nature of building computational tools but also due to the inherent problems arising from the variety and complexity of human languages. Breaking down language barriers is vital in enabling access to a number of recent technologies. This paper investigates the application of document classification methods to new Sinhalese datasets. This language is geographically isolated and rich with many of its own unique features. We will examine the interpretability of the classification models with a particular focus on the use of evolved Lucene search queries generated using a Genetic Algorithm (GA) as a method of document classification. We will compare the accuracy and interpretability of these search queries with other popular classifiers. The results are promising and are roughly in line with previous work on English language datasets.