Social media popularity prediction method and device based on visual semantic relationship

Abstract

The invention discloses a social media popularity prediction method and device based on a visual semantic relationship, wherein the method comprises the steps of extracting paired objects and predicate relationships between the paired objects from an image of a post through a pre-trained scene graph generator, and generating a < subject-predicate-object > relationship; encoding the relationship into semantic features by using a word vector model; encoding other data of the post to obtain text features, numerical features and additional user features, and connecting the text features, the numerical features and the additional user features with semantic features; aiming at the missing problem of users of partial posts of the test set in the training set, training two Catboost models respectively by using connected multi-modal features, and performing linear combination output to obtain a preliminary popularity score; and carrying out fine adjustment on the preliminary popularity score aiming at the post content by utilizing training set data, and balancing a model prediction error brought by user information, so as to obtain a final popularity score. The device comprises a processor and a memory. According to the invention, the accuracy of popularity prediction is improved.

Description

technical field [0001] The present invention relates to the field of visual relationship and social media popularity prediction, in particular to a social media popularity prediction method and device based on visual semantic relationship. Background technique [0002] In recent years, social media has played an increasingly important role in daily life. Millions of posts are uploaded and published through various social platforms, such as Weibo, Facebook, Flickr, etc., which have great impact on user experience and interpersonal communication. important influence. Therefore it is necessary to analyze the content of social media and further predict their popularity [1] (i.e. the number of hits, views, etc. of a post), in addition, building a prediction model of social media popularity can better serve some downstream tasks, such as information retrieval [2] , online advertising [3] and content recommendations [4] . [0003] In general, existing popularity prediction met...

AI Technical Summary

Problems solved by technology

In addition, the existing technology lacks favorable exploration of user information in the data set, and user ID (Uid) is an important feature of popularity prediction [5] , there will be cases where users with some posts in the test set do not exist in the training set, which will inevitably lead to a decline in the accuracy of the prediction

At the same time, the prediction model's dependence on user information will also lead to prediction bias.

[0004] Although researchers have done a lot of work in the field of social media popularity prediction and are committed to mining useful features in multi-type data, there is still some lack of visual relationship exploration contained in images of posts, and the test set is ignored. The problem that the user does not exist in the training set and the prediction bias caused by the dependence of the prediction model on user information

Images