1. MMC
  2. All Volumes and Issues
  3. Volume 10, Number 2, 2023
  4. Towards a polynomial approximation of support vector machine accuracy applied to Arabic tweet sentiment analysis

Towards a polynomial approximation of support vector machine accuracy applied to Arabic tweet sentiment analysis

MMC.
2023;
Volume 10, Number 2
: pp. 511–517
https://doi.org/10.23939/mmc2023.02.511
Received: March 04, 2023
Accepted: May 04, 2023

Mathematical Modeling and Computing, Vol. 10, No. 2, pp. 511–517 (2023)

Authors:
  1. Z. Banou
  2. S. Elfilali
  3. H. Benlahmar
1
Faculty of Sciences Ben M'Sik – Hassan II University
2
Faculty of Sciences Ben M'Sik – Hassan II University
3
Faculty of Sciences Ben M'Sik – Hassan II University

Machine learning algorithms have become very frequently used in natural language processing, notably sentiment analysis, which helps determine the general feeling carried within a text.  Among these algorithms, Support Vector Machines have proven powerful classifiers especially in such a task, when their performance is assessed through accuracy score and f1-score.  However, they remain slow in terms of training, thus making exhaustive grid-search experimentations very time-consuming.  In this paper, we present an observed pattern in SVM's accuracy, and f1-score approximated with a Lagrange polynomial.

Lagrange polynomial
SVM
machine learning
Sentiment Analysis
hyper-parameter optimization
  1. Yang L., Shami A.  On hyperparameter optimization of machine learning algorithms: Theory and practice.  Neurocomputing.  415, 295–316 (2020).
  2. Bergstra J., Bengio Y.  Random Search for Hyper-Parameter Optimization.  Journal of Machine Learning Research.  13, 281–305 (2012).
  3. Bergstra J., Bardenet R., Bengio Y., Kégl B.  Algorithms for Hyper-Parameter Optimization.  Advances In Neural Information Processing Systems.  24 (2011).
  4. Belete D. M., Huchaiah M. D.  Grid search in hyperparameter optimization of machine learning models for prediction of HIV/AIDS test results.  International Journal of Computers and Applications.  44 (9), 875–886 (2021).
  5. Elgeldawi E., Sayed A., Galal A. R., Zaki A. M.  Hyperparameter Tuning for Machine Learning Algorithms Used for Arabic Sentiment Analysis.  Informatics.  8 (4), 79 (2021).
  6. Woźniak M., Połap D., Napoli C., Tramontana E.  Graphic object feature extraction system based on Cuckoo Search Algorithm.  Expert Systems with Applications.  66, 20–31 (2016).
  7. Kennedy J., Eberhart R.  Particle swarm optimization.  Proceedings Of ICNN'95 – International Conference On Neural Networks.  4, 1942–1948 (1995).
  8. Połap D., Woźniak M.  Polar Bear Optimization Algorithm: Meta-Heuristic with Fast Population Movement and Dynamic Birth and Death Mechanism.  Symmetry.  9 (10), 203 (2017).
  9. Nabil M., Aly M., Atiya A.  ASTD: Arabic Sentiment Tweets Dataset.  Proceedings of The 2015 Conference on Empirical Methods in Natural Language Processing. 2515–2519 (2015).
  10. Mihi S., Ait B., El I., Arezki S., Laachfoubi N.  MSTD: Moroccan Sentiment Twitter Dataset.  International Journal of Advanced Computer Science and Applications.  11 (10), (2020).
  11. Elmadany A., Mubarak H., Magdy W.  ArSAS: An Arabic Speech-Act and Sentiment Corpus of Tweets (2018).
  12. Alowisheq A., Al-Twairesh N., Altuwaijri M., Almoammar A., Alsuwailem A., Albuhairi T., Alahaideb W., Alhumoud S.  MARSA: Multi-Domain Arabic Resources for Sentiment Analysis.  IEEE Access.  9, 142718–142728 (2021).