A method for identifying members of social network organizations based on twitter data

Abstract

The invention relates to a social network organization member identification method based on Twitter data, which is characterized in that it comprises the following steps: crawling users who pay attention to the public accounts of the target organization to form a candidate set; finding and determining users belonging to the target organization to form a seed set; Determine the score threshold and expected value; crawl each user's follow list and followed list, all tweets in the candidate set and extract the push relationship; for each user in the candidate set, calculate the identification factor according to the seed set, Use the evaluation model to calculate the score of each user; according to the given score threshold, select the users whose score is greater than the score threshold from the candidate set to form the result set; remove the result set generated in this round from the candidate set, and use the newly generated result The set is added to the seed set; iterated until the number of members in the seed set reaches the desired value. The method involved in the invention can excavate the members in the target organization, and the excavation accuracy is high.

Description

technical field [0001] The technical field of mass data analysis and mining of the present invention, more specifically relates to a social network organization member identification method based on Twitter data. Background technique [0002] A social network is a platform for information sharing, information dissemination, and information acquisition based on user relationships. It has penetrated into every aspect of our life, and it has broken through the information dissemination methods of traditional media. Users can freely produce information that they think is valuable, and share this information with friends in the form of short texts, pictures or videos. At the same time, users can also actively choose to become friends or fans of other users, and obtain information they are interested in anytime, anywhere. With the rise and rapid development of social networks, network life has become more colorful, and almost every netizen has participated in this new type of net...

AI Technical Summary

Problems solved by technology

[0004] The disadvantages of the above identification methods are: first, the social network members can only be divided into several communities, but it will not further determine the special relationship between users; second, only the user set of the social network is based on the Structural relevance or attribute similarity is divided into several user sets, and it cannot mine relevant members for a specific organization; third, these methods have many shortcomings, such as unstable iterations, unclear selection of user attribute features, etc.

Images