New approach for arabic named entity recognition on social media based on feature selection using genetic algorithm

Brahim Ait Benali, Soukaina Mihi, Ismail El Bazi, Nabil Laachfoubi


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.


arabic dialect; genetic algorithm; named entity recognition feature selection; NLP; social media; support vector machine;

Total views : 0 times

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

ISSN 2088-8708, e-ISSN 2722-2578