Two-layer classification and distinguished representations of users and documents for grouping and authorship identification

Abstract

Abstract-Most studies on authorship identification reported a drop in the identification result when the number of authors exceeds 20-25. In this paper, we introduce a new user representation to address this problem and split classification across two layers. There are at least 3 novelties in this paper. First, the two-layer approach allows applying authorship identification over larger number of authors (tested over 100 authors), and it is extendable. The authors are divided into groups that contain smaller number of authors. Given an anonymous document, the primary layer detects the group to which the document belongs. Then, the secondary layer determines the particular author inside the selected group. In order to extract the groups linking similar authors, clustering is applied over users rather than documents. Hence, the second novelty of this paper is introducing a new user representation that is different from document representation. Without the proposed user representation, the clustering over documents will result in documents of author(s) distributed over several clusters, instead of a single cluster membership for each author. Third, the extracted clusters are descriptive and meaningful of their users as the dimensions have psychological backgrounds. For authorship identification, the documents are labelled with the extracted groups and fed into machine learning to build classification models that predicts the group and author of a given document. The results show that the documents are highly correlated with the extracted corresponding groups, and the proposed model can be accurately trained to determine the group and the author identity.

User identification based on short text using recurrent deep learning

“…Many steps of preprocessing wrere done such as: removes images, videos, elicit text in tables, and delete empty posts, all that to produce group from 63,167 posts that represent purely dataset for this work. The classification percentageis high blooger for larger number posts is greater than 90% [11].…”

“…Mohtasseb and Ahmed identify the author (person) by text collection, features extraction by converting very blog post to a features vector and finally applied support vector machine (SVM) as the classification algorithm [11]. They used text that collected from LiveJournal 80,000 blog posts that contained 565 authors(person) with 140 posts as a rate for any user.…”

Author identification of literary works based on text analysis and deep learning

“…As a result, the author identification of Chinese texts has the following problems: first, the feature modeling of Chinese texts mostly relies on manual work, and different modeling is required according to the different characteristics of different corpora; second, the accuracy of classification largely depends on the size of corpus. Third, when the number of authors is large, the accuracy rate decreases significantly [ 7 ].…”