Communication Dans Un Congrès Année : 2021

Adopting Transition Point Technique for Persian Sentiment Analysis

Kia Dashtipour
  • Fonction : Auteur
  • PersonId : 1098661
Mandar Gogate
  • Fonction : Auteur
  • PersonId : 1098662
Alexander Gelbukh
  • Fonction : Auteur
  • PersonId : 1100262
Amir Hussain
  • Fonction : Auteur
  • PersonId : 1100263

Résumé

Sentiment analysis is used to analyses people's opinions, views and emotions towards different entities such as products, organizations, companies and events. People's opinions are important for most others during their decision-making process. For example, if someone wants to buy a product, they might want to know more about that product and the experiences of others with that product. Sentiment analysis is able to classify the reviews based on their polarity; even if reviews are expressed in a sentence or document, sentiment analysis is used to classify it into positive, negative or neutral reviews. In this paper, we proposed a framework using TF-IDF and transition point to detect polarity in Persian movie reviews. The proposed approach has been evaluated using different classifiers such as SVM, Naive Bayes, MLP and CNN. The experimental results show the transition point is more effective in comparison with traditional feature such as TF-IDF.

Fichier principal
Vignette du fichier
Transition_Point (2).pdf (142.61 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03258136 , version 1 (11-06-2021)

Licence

Identifiants

  • HAL Id : hal-03258136 , version 1

Citer

Kia Dashtipour, Mandar Gogate, Alexander Gelbukh, Amir Hussain. Adopting Transition Point Technique for Persian Sentiment Analysis. ICOTEN, Jun 2021, Glasgow, France. ⟨hal-03258136⟩
148 Consultations
149 Téléchargements

Partager

  • More