Method for improving accuracy of influence of user generate content (UGC) information of social network
A technology of social networking and influence, applied in special data processing applications, instruments, electrical and digital data processing, etc., can solve problems such as deviation of information influence, and achieve the effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0072] Figure 5 A UGC structure diagram for this embodiment, such as Figure 5 As shown, the UGC includes 4 users: User 1, User 2, User 3, and User 4. User 1 is the information publisher, and the keywords released are A, B, and C; users 2 and 3 respectively reply to user 1 directly, and the keywords posted by user 2 are A, C, D, and the keywords posted by user 3 are B, F; User 4 directly replied to User 2 with the keywords C and F. Interest network community number is represented by r, r 1 = 1, r 2 = 1, r 3 = 2, r 4 = 3; the fan network community number is represented by f, f 1 = 1, f 2 = 2, f 3 = 1, f 4 =3. User 2 and User 4 are fans of the information publisher User 1. In this embodiment, the path coefficients between the various factors in the member participation mechanism are assigned as: a 1 =0.333,a 2 =0.824,a 3 =0.624,a 4 = 0.437. Image 6 Be the flow chart of this embodiment, such as Image 6 shown, including the following steps:
[0073] Step 601: ...
Embodiment 2
[0087] Method Embodiment 1 Taking UGC with less user participation as an example, how to calculate the influence of social network UGC information by the technical solution of the present invention is explained. The program is further explained.
[0088] User information includes a total of 181,841 user IDs, IDs of their fans, IDs of posts published in this forum, and IDs of replies to posts in this forum; post information includes a total of 43,609 post IDs, the serial number of each floor in the post, and the publisher ID and its content. By judging whether the post contains the boutique symbol of the forum administrator, 827 posts are selected from the post information as the manual tagged boutique post set, and the other posts are regarded as the non-fine post collection. Due to the huge amount of data, 9173 posts were randomly selected from the collection of non-excellent posts and 827 artificially marked high-quality posts were mixed into a sample of 10,000 posts, and t...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 