Topic Modelling Used to Improve Arabic Web Pages Clustering

Abstract

Topic modelling main purpose is to have machineunderstandable and semantic annotation to textual contents of Web.It aim to extract knowledge rather than unrelated information. In this paper, we evaluate the impact of using topic model (which intended to represent the documents like a combination of topics where each topic is a mix of vectors) in improving documents clustering results. We have compared the results of clustering using PLSA or LSA. The experiments performed on a set of common newspaper websites that have highly dimensional data and we use Purity, Mean intra-cluster distance (MICD) and Davies-Bouldin index (DBI) for clustering evaluation. Thus, we acquired favorable clustering results, especially in the context of the Arabic language as PLSA were effective in minimizing MICD, expanding purity and bringing down DBI.

Enhancing topic clustering for Arabic security news based on k‐means and topic modelling

“…It found the need to combine the two models for specific data clustering. The KM findings deviate from research by Zhao et al [23] but are similar to other studies such as Alghamdi et al [20].…”

“…The study found that the rate of perplexity change is an integral heuristic approach for selecting the best topics for clustering. The findings are in tandem with other research that investigates the model for topics that can improve the processing of clustering Arabic web pages [20]. The point of conformance is that the two studies agree that the primary purpose of using this model is to provide a framework for semantic annotation or machine‐understandable processes for the textual context of Arabic webpages [23, 20].…”

“…The topic modelling methods help to learn and automate the topic analysis. By using such a technique, users do not have to manually view entire documents and detect covert topics and keywords enclosed in each topic [20]. Figure 1 presents the process of the work approach by obtaining the clustering topics from website news related to information security based on the article documents and collecting the text data into the data set.…”

“…[21] Adopted KM clustering of the document and found that it met the semantic extraction proposed by Alghamdi and Selamat [20].…”

“…[21] Adopted KM clustering of the document and found that it met the semantic extraction proposed by Alghamdi and Selamat [20]. [19] The study used clustering techniques and generative models and found that combining the KM clustering algorithm and LDA helped to map large data texts.…”