SavedAdd your journal

Journals / Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi / 2018 / Cilt: 24 - Sayı: 2

The impact of term weighting method on Twitter sentiment analysis

Twitter duygu analizinde terim ağırlıklandırma yönteminin etkisi

Önder ÇOBAN
Gülşah TÜMÜKLÜ ÖZYER
Pages
283–291
Publication Date
2018-04-30
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

According to the experimental results, the most effective term weighting method that can be used in Twitter sentiment analysis studies is suggested.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Term weighting is an important step which has direct impact on the result in classical text classification.
📊
Key Findings & Data:Sentiment classification of Twitter feeds performed using topic model generated with Latent Dirichlet Allocation (LDA) method.
💡
Conclusion & Impact:According to the experimental results, the most effective term weighting method that can be used in Twitter sentiment analysis studies is suggested.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Twitter · Duygu analizi · Terim ağırlıklandırma

Abstract

Term weighting is an important step which has direct impact on the result in classical text classification. However, the behavior of the term weighting method may vary depending on different preprocessing techniques in sentiment analysis which considered as a text classification task. In this study, term weighted methods which are newly proposed for various research areas such as information retrieval, text classification and document filtering, performed to investigate effect on results for Twitter sentiment analysis. In feature extraction phase, two different models are used including Bag of Words (BoW) and character level N-gram. The experiments conducted on data sets consist of Turkish and English Twitter feeds. Sentiment classification of Twitter feeds performed using topic model generated with Latent Dirichlet Allocation (LDA) method. The Support Vector Machine (SVM) algorithm is employed in the classification stage. According to the experimental results, the most effective term weighting method that can be used in Twitter sentiment analysis studies is suggested.

Özet

Terim ağırlıklandırma, metin sınıflandırmada sonuçlar üzerinde doğrudan etkili olan önemli bir adımdır. Ancak, bir metin sınıflandırma problemi olarak ele alınan duygu analizinde farklı önişleme tekniklerine bağlı olarak ağırlıklandırma yönteminin davranışı değişebilmektedir. Bu çalışmada bilgi getirimi, metin sınıflandırma, doküman filtreleme gibi farklı çalışma alanları için yakın zamanda önerilen yöntemler Twitter duygu analizinde uygulanmış ve sonuçlar üzerindeki etkisi incelenmiştir. Öznitelikler çıkarılırken kelime torbası (BoW) ve karakter seviye N-gram olmak üzere iki farklı model kullanılmıştır. Deneyler Türkçe ve İngilizce Twitter mesajlarından oluşan veri kümeleri üzerinde uygulanmıştır. Twitter mesajlarının duygu sınıflandırması, Gizli Dirichlet Ataması (LDA) tabanlı konu modeli ile gerçekleştirilmiştir. Sınıflandırma aşamasında ise Destek Vektör Makinesi (SVM) algoritması kullanılmıştır. Deneysel sonuçlara göre, Twitter duygu analizi çalışmalarında kullanılabilecek en etkili terim ağırlıklandırma yöntemi önerilmiştir.

🔖

Cite This Article

ÇOBAN, Ö., ÖZYER, G. T. (2018). The impact of term weighting method on Twitter sentiment analysis. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 24 - Sayı: 2, 283–291. https://ajindex.com/articles/42390

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (14)

  1. Patra A, Singh D. “A survey report on text classification with different term weighing methods and comparison between classification algorithms”. International Journal of Computer Applications, 75(7), 2013.
  2. Prabowo R, Thelwall M. “Sentiment analysis: A combined approach”. Journal of Informetrics, 3(2), 143-157, 2009.
  3. Paltoglou G, Thelwall M. “A study of information retrieval weighting schemes for sentiment analysis”. 48th Annual Meeting of the Association for Computational Linguistics, Stroudsburg, USA, 11-16 July 2010.
  4. Çetin M, Amasyalı MF. “Supervised and traditional term weighting methods for sentiment analysis”. In Signal Processing and Communications Applications Conference (SIU), Girne, KKTC, 24-26 April 2013.
  5. Aizawa A. “An information-theoretic perspective of tf–idf measures”. Information Processing & Management, 39(1), 45-65, 2003.
  6. Salton G, Buckley C. “Term-weighting approaches in automatic text retrieval”. Information processing & management, 24(5), 513-523, 1988.
  7. Robertson S, Zaragoza H, Taylor M. “Simple BM25 extension to multiple weighted fields”. 13th ACM International Conference on Information and Knowledge Management, New York, USA, 08-13 November 2004.
  8. Lan M, Tan CL, Low HB. “Proposing a new term weighting scheme for text categorization”. Association for the Advancement of Artificial Intelligence, Boston, USA, 16-20 June 2006.
  9. Reed JW, Jiao Y, Potok TE, Klump BA, Elmore MT, Hurson A R. “TF-ICF: A new term weighting scheme for clustering dynamic data streams”. In ICMLA'06. 5th International Conference on Machine Learning and Applications, Florida, USA, 14-16 December 2006.
  10. Polettini N. “The vector space model in information retrieval-term weighting problem”. Entropy, 1-9, 2004.
  11. Chen LS, Chang CW. “A new term weighting method by introducing class information for sentiment classification of textual data”. International Multi Conference of Engineers and Computer Scientists, Hong Kong, China, 16-18 March 2011.
  12. Deng ZH, Luo KH, Yu HL. “A study of supervised term weighting scheme for sentiment analysis”. Expert Systems with Applications, 41(7), 3506-3513, 2014.
  13. Gasanova T, Sergienko R, Akhmedova S, Semenkin E, Minker W. “Opinion mining and topic categorization with novel term Weighting”. 5th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Baltimore, Maryland, USA, 27 June 2014.
  14. Jung Y, Park H, Du D. “A Balanced term-weighting scheme for improved document comparison and classification”. Preprint, 2001. Ka