Abstract
Many features can be extracted from the massive volume of data in different types that are available nowadays on social media. The growing demand for multimedia applications was an essential factor in this regard, particularly in the case of text data. Often, using the full feature set for each of these activities can be time-consuming and can also negatively impact performance. It is challenging to find a subset of features that are useful for a given task due to a large number of features. In this paper, we employed a feature selection approach using the genetic algorithm to identify the optimized feature set. Afterward, the best combination of the optimal feature set is used to identify and classify the Arabic named entities (NEs) based on support vector. Experimental results show that our system reaches a state-of-the-art performance of the Arab NER on social media and significantly outperforms the previous systems.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have