Twitter Influence - Characterization of Twitter Profiles, with an application to offline influence detection - Archive ouverte HAL Access content directly
Software Year : 2014

Twitter Influence - Characterization of Twitter Profiles, with an application to offline influence detection

Abstract

These scripts are meant to extract certain features from raw Twitter data describing Twitter users (tweets, profile info, as well as external data). Once the features are extracted, various forms of SVMs are trained, and logistic regressions are performed, to classify and rank the users. These operations are conducted on different subgroups of features. The details of the process are given in the publications mentioned in the readme file. The scripts were applied to the classification/ranking of Twitter users in terms of offline influence, based on the RepLab 2014 dataset.

Cite

Jean-Valère Cossu, Nicolas Dugué, Vincent Labatut. Twitter Influence - Characterization of Twitter Profiles, with an application to offline influence detection. 2014, ⟨swh:1:dir:1343d720d6c3e19fa6124fd30fe23a0fa737e8e0;origin=https://hal.archives-ouvertes.fr/hal-02179513;visit=swh:1:snp:d08ff83162d7e6cf24502c4114e02e50d66bf1b0;anchor=swh:1:rev:cd96f9629ed1cfcf2bf57250db477194d8497e75;path=/⟩. ⟨hal-02179513⟩
81 View
24 Download

Share

Gmail Mastodon Facebook X LinkedIn More