Feature selection based on ACO and knowledge graph for Arabic text classification

Abstract

ABSTRACT Nowadays, multi-class learning processes have attracted a vast amount of attention due to their complexities and progressive development in various fields. This study focuses on the prediction of semantic categories of Arabic hadith texts by combining the Knowledge-Graph (KG) with the Ant Colony Optimisation (ACO) method. Knowledge-Graph is constructed based on the correlation between features and categories. The links’ weights depend on how frequently the features and the categories occur together, either directly or indirectly. Knowledge-Graph also directly gauges the weights of the links among features. Finally, the ants traverse the graph to select features the most prominent. Features are important whenever they are mentioned frequently in Hadith texts, and they belong to one or fewer categories. It is worth considering that the more relationships between one feature and multiple categories, the less likely it is to be selected. In our analytical experiments, six famous books of the Prophetic Sunnah were used, including more than thirty thousand hadiths with a number of categories slightly under 120. On the experimental side, we found promising results when the ACO-KG model has combined with machine learning classifiers, namely an increase of 3% in the classification task.