Abstract

With the number of films released each year, the movie review website is becoming more popular. One of the most referenced movie review websites is Rotten Tomatoes. Rotten Tomatoes recommend films based on their Tomatometer. Tomatometer represents the percentage of professional critic reviews that are positive or negative for a given film or television show. While fresh reviews represent positive sentiment, rotten reviews mean that the movie critics give the movie negative sentiments. Unfortunately, the method to determine the given score is not available to the public. Thus, the public does not know which parameter affect the prediction of the sentiment. This paper proposes a new method to predict the sentiment of the movie on the rotten tomatoes by combining the sentiment score from SentiWordnet and expert original score. the result of the experiment shows that the proposed method gives better F measure compared to those of the other methods with the value of 0.97.

Original languageEnglish
Title of host publicationProceedings - 2018 International Seminar on Application for Technology of Information and Communication
Subtitle of host publicationCreative Technology for Human Life, iSemantic 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages202-206
Number of pages5
ISBN (Electronic)9781538674864
DOIs
Publication statusPublished - 27 Nov 2018
Event3rd International Seminar on Application for Technology of Information and Communication, iSemantic 2018 - Semarang, Indonesia
Duration: 21 Sept 201822 Sept 2018

Publication series

NameProceedings - 2018 International Seminar on Application for Technology of Information and Communication: Creative Technology for Human Life, iSemantic 2018

Conference

Conference3rd International Seminar on Application for Technology of Information and Communication, iSemantic 2018
Country/TerritoryIndonesia
CitySemarang
Period21/09/1822/09/18

Keywords

  • Rotten tomatoes
  • Sentiment analysis
  • Sentiwordnet

Fingerprint

Dive into the research topics of 'Prediction of Movie Sentiment based on Reviews and Score on Rotten Tomatoes using SentiWordnet'. Together they form a unique fingerprint.

Cite this