Keyword extraction for film reviews based on social network analysis and natural language technology

Quan Yanan,Tan Fuqiang,N Hamid,S Zhou

doi:10.1051/e3sconf/202018903019

Quan Yanan, Tan Fuqiang + Show 2 more

Open Access

https://doi.org/10.1051/e3sconf/202018903019

Copy DOI

Abstract

At present, there are many movie reviews appear on main stream websites, and these evaluations are quite different to the same movie. As a customer, how to choose your favorite movie and television program? To solve this problem, this study attempts to use the semantic analysis of word vectors (Word2vec) semantic analysis in machine learning as a research tool to mine a large number of movie reviews. The research shows that most movie reviews have a certain theme cohesion and their semantic network has quite connected. Through the use of social network analysis and the use of Word2vec word vector technology in natural language processing, it is possible to present a streamlined movie review based on movie review network semantics and keyword extraction, thus helping to select the favorite movie review.

Highlights

Movie review, or film review for short, it means the analysis and comment on the director, actors, lenses, photography, plot, clues, environment, colors, lighting, audio-visual language, prop functions, transitions, and edits of a movie
By analyzing, appraising and evaluating the aesthetic value, cognitive value, social significance, lens language that displayed in the screen, the purpose of movie review is to achieve the goal of shooting the film, to explain the theme expressed in the film, by analyzing the success or failure, the gains and losses of the film, it helps the directors to broaden their horizons and improve their creative level, so as to promote the prosperity and development of film art; at the same time, they can affect the audience's understanding and appreciation of the film through analysis and evaluation, and improve the audience's appreciation level, thereby indirectly promoting the development of film art
This study uses Social Network Analysis (SNA) combined with Word2vec word vector technology in natural language processing, which is intended to explore the internal relationships and keywords of movie reviews to help the audience in selecting their favorite movies

Summary

Introduction

Film review for short, it means the analysis and comment on the director, actors, lenses, photography, plot, clues, environment, colors, lighting, audio-visual language, prop functions, transitions, and edits of a movie. Previous studies on film criticism have mostly used film criticism content as qualitative analysis research materials, and tapped the essence of related film criticism. A Khan, MA Gul (2020) studied movie reviews using a sorting algorithm based on supervised learning and graphs. H Park, K Kim (2019) used the CNN-LSTM model to classify the sentiment of movie reviews. F WU, S LI, G ZHOU (2019) used the LSTM model to classify the content of movie reviews. This study uses Social Network Analysis (SNA) combined with Word2vec word vector technology in natural language processing, which is intended to explore the internal relationships and keywords of movie reviews to help the audience in selecting their favorite movies

Research data

Research process

Introduction to Social Network Analysis and Exploration of Semantic Network

Natural language mining results based on word2vec

Conclusion