<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">ntv</journal-id><journal-title-group><journal-title xml:lang="ru">Научно-технический вестник информационных технологий, механики и оптики</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific and Technical Journal of Information Technologies, Mechanics and Optics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2226-1494</issn><issn pub-type="epub">2500-0373</issn><publisher><publisher-name>Университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/2226-1494-2024-24-6-982-990</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-404</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>КОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>COMPUTER SCIENCE</subject></subj-group></article-categories><title-group><article-title>Анализ настроений арабских твитов с использованием контролируемого машинного обучения</article-title><trans-title-group xml:lang="en"><trans-title>Sentiment analysis of Arabic tweets using supervised machine learning</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0005-3312-7950</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Бенабдаллах</surname><given-names>А.</given-names></name><name name-style="western" xml:lang="en"><surname>Benabdallah</surname><given-names>A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Бенабдаллах Али - PhD, преподаватель, </p><p>Тлемсен, 13000</p></bio><bio xml:lang="en"><p>Ali Benabdallah - PhD, Lecturer,</p><p>Tlemcen, 13000</p></bio><email xlink:type="simple">benabdallah.a13@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Абдеррахим</surname><given-names>М. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Abderrahim</surname><given-names>M. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Абдеррахим Мохаммед Алаеддин - PhD, преподаватель,</p><p>Тлемсен, 13000</p></bio><bio xml:lang="en"><p>Mohammed Alaeddine Abderrahim - PhD, Lecturer,</p><p>Tlemcen, 13000</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Мокри</surname><given-names>М.</given-names></name><name name-style="western" xml:lang="en"><surname>Mokri</surname><given-names>M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Мокри Мохаммед - исследователь,</p><p>Тлемсен, 13000</p></bio><bio xml:lang="en"><p>Mohammed Mokri - Researcher,</p><p>Tlemcen, 13000</p></bio><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Высшая школа менеджмента Тлемсена</institution><country>Алжир</country></aff><aff xml:lang="en"><institution>Higher school of Management of Tlemcen</institution><country>Algeria</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Университет Тлемсена</institution><country>Алжир</country></aff><aff xml:lang="en"><institution>University of Tlemcen</institution><country>Algeria</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>29</day><month>12</month><year>2024</year></pub-date><volume>24</volume><issue>6</issue><fpage>982</fpage><lpage>990</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Бенабдаллах А., Абдеррахим М.А., Мокри М., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Бенабдаллах А., Абдеррахим М.А., Мокри М.</copyright-holder><copyright-holder xml:lang="en">Benabdallah A., Abderrahim M.A., Mokri M.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://ntv.elpub.ru/jour/article/view/404">https://ntv.elpub.ru/jour/article/view/404</self-uri><abstract><p>Растущий объем пользовательского контента на платформах социальных сетей требует эффективных инструментов для понимания общественных настроений. В работе представлен подход к анализу настроений арабских твитов с использованием контролируемых методов машинного обучения. Исследована производительность трех популярных алгоритмов — опорных векторных машин (Support Vector Machines, SVM), наивного байесовского алгоритма (Naive Bayes, NB) и логистической регрессии (Logistic Regression, LR) — на двух отдельных корпусах: арабском корпусе текстов настроений (Arabic Sentiment Text Corpus, ASTC) и корпусе арабских твитов. Подход содержал четыре теста, оценивающих влияние характеристик корпуса: метода предварительной обработки, метода взвешивания и использования N-грамм на точность классификации. Первый тест позволил установить, что выбор корпуса значительно влияет на производительность модели, при этом SVM показал высокую точность на структурированном ASTC, в то время как NB лучше работает с неформальными арабскими твитами. Во втором тесте предварительная обработка, включая удаление знаков препинания и стоп-слов, привела к заметному улучшению точности классификации для арабских твитов, но оказала минимальное или даже отрицательное влияние на ASTC. Третий тест показал, что включение N-грамм дало незначительное улучшения для NB и LR в более структурированных текстах, в то время как его влияние на твиты было незначительным. Четвертый тест позволил сравнить различные методы взвешивания, показав, что SVM выиграл по сравнению с методом взвешивания TF-IDF, в то время как производительность NB оставалась стабильной независимо от подхода к взвешиванию. Полученные результаты подчеркивают важность адаптации стратегий предварительной обработки и извлечения признаков к конкретным характеристикам набора данных, что в итоге повышает точность анализа настроений в контекстах арабского языка.</p></abstract><trans-abstract xml:lang="en"><p>The increasing volume of user-generated content on social media platforms necessitates effective tools for understanding public sentiment. This study presents an approach to sentiment analysis of Arabic tweets using supervised machine learning techniques. We explored the performance of three popular algorithms — Support Vector Machines (SVM), Naive Bayes (NB), and Logistic Regression (LR) — on two distinct corpora: the Arabic Sentiment Text Corpus (ASTC) and a dataset of Arabic tweets. Our methodology involved four tests assessing the impact of corpus characteristics, preprocessing techniques, weighting methods, and the use of N-grams on classification accuracy. The first test established that the choice of corpus significantly influences model performance, with SVM showing superior accuracy on the structured ASTC, while NB excelled with the informal Arabic tweets. In the second test, preprocessing steps, including the removal of punctuation and stop-words, led to a noticeable improvement in classification accuracy for the Arabic tweets but had minimal or even negative effects on the ASTC. The third test indicated that incorporating N-grams yielded modest improvements for NB and LR in more structured texts, while its impact on tweets was negligible. Finally, the fourth test compared different weighting techniques, revealing that SVM benefitted from the Term Frequency-Inverse Document Frequency weighting method, while NB performance remained stable regardless of the weighting approach. These findings underscore the importance of tailoring preprocessing and feature extraction strategies to the specific characteristics of the dataset, ultimately enhancing the accuracy of sentiment analysis in Arabic language contexts.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>анализ настроений на арабском языке (ASA)</kwd><kwd>машинное обучение</kwd><kwd>классификатор</kwd><kwd>полярность</kwd><kwd>Twitter</kwd></kwd-group><kwd-group xml:lang="en"><kwd>Arabic sentiment analysis (ASA)</kwd><kwd>machine learning</kwd><kwd>classifier</kwd><kwd>polarity</kwd><kwd>Twitter</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Mataoui M., Zelmati O., Boumechache M. A Proposed lexicon-based sentiment analysis approach for the vernacular Algerian Arabic // Research in Computing Science. 2016. V. 110. P. 55–70. https://doi.org/10.13053/rcs-110-1-5</mixed-citation><mixed-citation xml:lang="en">Mataoui M., Zelmati O., Boumechache M. A Proposed lexicon-based sentiment analysis approach for the vernacular Algerian Arabic. Research in Computing Science, 2016, vol. 110, pp. 55–70. https://doi.org/10.13053/rcs-110-1-5</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Al-Kabi M., Gigieh A., Alsmadi I., Wahsheh H., Haidar M. An opinion analysis tool for colloquial and standard Arabic // Proc. of the fourth International Conference on Information and Communication Systems (ICICS 2013). 2013.</mixed-citation><mixed-citation xml:lang="en">Al-Kabi M., Gigieh A., Alsmadi I., Wahsheh H., Haidar M. An opinion analysis tool for colloquial and standard Arabic. Proc. of the fourth International Conference on Information and Communication Systems (ICICS 2013), 2013.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Pang B., Lee L. Opinion mining and sentiment analysis // Foundations and Trends in Information Retrieval. 2008. V. 2(1-2). P. 1–135. https://doi.org/10.1561/1500000011</mixed-citation><mixed-citation xml:lang="en">Pang B., Lee L. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2008, vol. 2(1-2), pp. 1–135. https://doi.org/10.1561/1500000011</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Taboada M., Brooke J., Tofiloski M., Voll K., Stede M. Lexicon-based methods for sentiment analysis // Computational Linguistics. 2011. V. 37. N 2. P. 267–307. https://doi.org/10.1162/coli_a_00049</mixed-citation><mixed-citation xml:lang="en">Taboada M., Brooke J., Tofiloski M., Voll K., Stede M. Lexicon-based methods for sentiment analysis. Computational Linguistics, 2011, vol. 37, no. 2, pp. 267–307. https://doi.org/10.1162/coli_a_00049</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Ding X., Liu B., Yu P.S. A holistic lexicon-based approach to opinion mining // WSDM ‘08: Proc. of the 2008 International Conference on Web Search and Data Mining. 2008. P. 231–240. https://doi.org/10.1145/1341531.1341561</mixed-citation><mixed-citation xml:lang="en">Ding X., Liu B., Yu P.S. A holistic lexicon-based approach to opinion mining. WSDM ‘08: Proc. of the 2008 International Conference on Web Search and Data Mining, 2008, pp. 231–240. https://doi.org/10.1145/1341531.1341561</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Kumar A., Sebastian T.M. Sentiment analysis on twitter // IJCSI International Journal of Computer Science Issues. 2012. V. 9. N 3. P. 372–378.</mixed-citation><mixed-citation xml:lang="en">Kumar A., Sebastian T.M. Sentiment analysis on twitter. IJCSI International Journal of Computer Science Issues, 2012, vol. 9, no. 3, pp. 372–378.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Klenner M., Petrakis S., Fahrni A. Robust compositional polarity classification // Proc. of the International Conference RANLP. 2009. P. 180–184.</mixed-citation><mixed-citation xml:lang="en">Klenner M., Petrakis S., Fahrni A. Robust compositional polarity classification. Proc. of the International Conference RANLP, 2009, pp. 180–184.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Pak A., Paroubek P. Twitter as a corpus for sentiment analysis and opinion mining // Proc. of the Seventh International Conference on Language Resources and Evaluation (LREC’10). 2010.</mixed-citation><mixed-citation xml:lang="en">Pak A., Paroubek P. Twitter as a corpus for sentiment analysis and opinion mining. Proc. of the Seventh International Conference on Language Resources and Evaluation (LREC’10), 2010.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Al-Kabi M., Al-Ayyoub M., Alsmadi I., Wahsheh H. A prototype for a standard Arabic sentiment analysis corpus // International Arab Journal of Information Technology. 2016. V. 13. N 1A. P. 163– 170.</mixed-citation><mixed-citation xml:lang="en">Al-Kabi M., Al-Ayyoub M., Alsmadi I., Wahsheh H. A prototype for a standard Arabic sentiment analysis corpus. International Arab Journal of Information Technology, 2016, vol. 13, no. 1A, pp. 163– 170.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Oueslati O., Cambria E., HajHmida M.B., Ounelli H. Review of sentiment analysis research in Arabic language // Future Generation Computer Systems. 2020. V. 112. P. 408–430. https://doi.org/10.1016/j.future.2020.05.034</mixed-citation><mixed-citation xml:lang="en">Oueslati O., Cambria E., HajHmida M.B., Ounelli H. Review of sentiment analysis research in Arabic language. Future Generation Computer Systems, 2020, vol. 112, pp. 408–430. https://doi.org/10.1016/j.future.2020.05.034</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Ghallab A., Mohsen Y., Ali Y. Arabic sentiment analysis: A systematic literature review // Applied Computational Intelligence and Soft C o m p u t i n g . 2 0 2 0 . V. 2020. P. 403128. https://doi.org/10.1155/2020/7403128</mixed-citation><mixed-citation xml:lang="en">Ghallab A., Mohsen Y., Ali Y. Arabic sentiment analysis: A systematic literature review. Applied Computational Intelligence and Soft Computing, 2020, vol. 2020, pp. 403128. https://doi.org/10.1155/2020/7403128</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Duwairi R., Marji R., Sha’ban N., Rushaidat S. Sentiment Analysis in Arabic tweets // Proc. of the 2014 5th International Conference on Information and Communication Systems (ICICS). 2014. P. 1–6. https://doi.org/10.1109/iacs.2014.6841964</mixed-citation><mixed-citation xml:lang="en">Duwairi R., Marji R., Sha’ban N., Rushaidat S. Sentiment Analysis in Arabic tweets. Proc. of the 2014 5th International Conference on Information and Communication Systems (ICICS), 2014, pp. 1–6. https://doi.org/10.1109/iacs.2014.6841964</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Bolbol N.K., Maghari A.Y. Sentiment analysis of Arabic tweets using supervised machine learning // Proc. of the 2020 International Conference on Promising Electronic Technologies (ICPET). 2020. P. 89–93. https://doi.org/10.1109/ICPET51420.2020.00025</mixed-citation><mixed-citation xml:lang="en">Bolbol N.K., Maghari A.Y. Sentiment analysis of Arabic tweets using supervised machine learning. Proc. of the 2020 International Conference on Promising Electronic Technologies (ICPET), 2020, pp. 89–93. https://doi.org/10.1109/ICPET51420.2020.00025</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Heikal M., Torki M., El-Makky N. Sentiment analysis of Arabic Tweets using deep learning // Procedia Computer Science. 2018. V. 142. P. 114–122. https://doi.org/10.1016/j.procs.2018.10.466</mixed-citation><mixed-citation xml:lang="en">Heikal M., Torki M., El-Makky N. Sentiment analysis of Arabic Tweets using deep learning. Procedia Computer Science, 2018, vol. 142, pp. 114–122. https://doi.org/10.1016/j.procs.2018.10.466</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Alhamid M., Alsahli S., Rawashdeh M., Alrashoud M. Detection and visualization of Arabic emotions on social emotion map // Proc. of the International Symposium on Multimedia (ISM). 2017. P. 378–381. https://doi.org/10.1109/ISM.2017.76</mixed-citation><mixed-citation xml:lang="en">Alhamid M., Alsahli S., Rawashdeh M., Alrashoud M. Detection and visualization of Arabic emotions on social emotion map. Proc. of the International Symposium on Multimedia (ISM), 2017, pp. 378–381. https://doi.org/10.1109/ISM.2017.76</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Al-Thubaity A., Alqahtani Q., Aljandal A. Sentiment lexicon for sentiment analysis of Saudi dialect tweets // Procedia Computer Science. 2018. V. 142. P. 301–307. https://doi.org/10.1016/j. procs.2018.10.494</mixed-citation><mixed-citation xml:lang="en">Al-Thubaity A., Alqahtani Q., Aljandal A. Sentiment lexicon for sentiment analysis of Saudi dialect tweets. Procedia Computer Science, 2018, vol. 142, pp. 301–307. https://doi.org/10.1016/j. procs.2018.10.494</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Assiri A., Emam A., Al-Dossari H. Towards enhancement of a lexicon-based approach for Saudi dialect sentiment analysis // Journal of Information Science. 2018. V. 44. N 2. P. 184–202. https://doi.org/10.1177/0165551516688143</mixed-citation><mixed-citation xml:lang="en">Assiri A., Emam A., Al-Dossari H. Towards enhancement of a lexicon-based approach for Saudi dialect sentiment analysis. Journal of Information Science, 2018, vol. 44, no. 2, pp. 184–202. https://doi.org/10.1177/0165551516688143</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Alqurashi T. Arabic sentiment analysis for twitter data: A systematic literature review // Engineering, Technology &amp; Applied Science Research. 2023. V. 13. N 2. P. 10292–10300. https://doi.org/10.48084/etasr.5662</mixed-citation><mixed-citation xml:lang="en">Alqurashi T. Arabic sentiment analysis for twitter data: A systematic literature review. Engineering, Technology &amp; Applied Science Research, 2023, vol. 13, no. 2, pp. 10292–10300. https://doi.org/10.48084/etasr.5662</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Liu B. Sentiment Analysis: Mining Opinions, Sentiments, and Emotions / 2nd ed. Cambridge University Press, 2020. 448 p.</mixed-citation><mixed-citation xml:lang="en">Liu B. Sentiment Analysis: Mining Opinions, Sentiments, and Emotions. 2nd ed. Cambridge University Press, 2020, 448 p.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
