A Method for Automatically Generating Movie Tags Based on Movie Reviews

A technology of automatic generation and labeling, which is applied in the fields of electrical digital data processing, instruments, calculations, etc., can solve the problems of few social labels, difficult to cover movies, time-consuming and labor-intensive problems, etc.

Active Publication Date: 2021-06-25
SUN YAT SEN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, currently, for unreleased movies or unpopular movies, due to the very small number of users watching them, these movies usually have very few or no social tags, and the number of these movies is far greater than that of movies with richer social tags
Manually labeling this part of the movie is not only time-consuming and laborious, but also difficult to cover all aspects of the movie more comprehensively

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Method for Automatically Generating Movie Tags Based on Movie Reviews

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] A method for automatically generating movie tags based on movie reviews, comprising the following steps:

[0026] Step S1: Obtain movie reviews, attributes and their corresponding social tags of all movies on the platform as a training set;

[0027] Step S2: If the number of social tags of a certain movie is lower than the set threshold, tags are automatically extracted from its movie reviews through the tag completion algorithm, so as to add tags to the movie;

[0028] Step S3: Calculate the similarity of attributes for every two movies in the training set, and calculate the similarity of social label sets for every two movies, so as to construct a new data set, and use it to build a regression learner to learn from attributes to similarity map;

[0029] Step S4: Based on the similarity predicted by the regression learner, the K-nearest neighbor method is used to determine the top K most similar movies in the training set for each unlabeled movie, and the multiple set...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention proposes an algorithm for automatically generating movie labels based on film reviews. The algorithm in the present invention fully considers the missing problem existing in the data set of currently labeled movies. First, an unsupervised algorithm with weights is used to automatically train Set complementary labels. At the same time, the present invention also fully considers the relationship between the similarity of the attributes of the two movies and the similarity of the labels, and predicts the mapping from the attributes to the similarity of the labels with the method of machine learning, instead of using simple similarities such as cosine Similarity calculates a rough similarity relationship. Finally, after using the traditional K-nearest neighbor algorithm to obtain multiple sets of candidate labels, this method does not use simple evaluation criteria to sort and select the label set, but uses a graph algorithm based on the co-occurrence relationship of labels to determine the order of candidate labels, so that Decide on the final label set.

Description

technical field [0001] The invention relates to the field of artificial intelligence, and more specifically, to a method for automatically generating movie labels based on movie reviews. Background technique [0002] Because of its rich elements, movies quickly become one of the necessary leisure ways in people's daily life. The market for movies is getting bigger and bigger, and there are more and more types of movies. A wide variety of movies and the length of the movie make it impossible for users to browse a movie in its entirety. For upcoming movies, a better way for users to know about a movie usually includes introduction, trailer, other users’ reviews and movie tags. But for some older or less popular movies, users usually only know the introduction and movie tags. Therefore, the social tags of movies are of great significance. They can help recommendation systems improve the accuracy of movies recommended for users, help platforms that provide movie information fi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/783
Inventor 吴迪吴灿锐
Owner SUN YAT SEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap