Explainable Authorship Verification in Social Media via Attention-based Similarity Learning

@article{Boenninghoff2019ExplainableAV,
  title={Explainable Authorship Verification in Social Media via Attention-based Similarity Learning},
  author={Benedikt T. Boenninghoff and Steffen Hessler and Dorothea Kolossa and Robert M. Nickel},
  journal={2019 IEEE International Conference on Big Data (Big Data)},
  year={2019},
  pages={36-45}
}
Authorship verification is the task of analyzing the linguistic patterns of two or more texts to determine whether they were written by the same author or not. The analysis is traditionally performed by experts who consider linguistic features, which include spelling mistakes, grammatical inconsistencies, and stylistics for example. Machine learning algorithms, on the other hand, can be trained to accomplish the same, but have traditionally relied on so-called stylometric features. The… Expand
LG4AV: Combining Language Models and Graph Neural Networks for Author Verification
TLDR
The novel approach LG4AV which combines language models and graph neural networks for authorship verification is presented and the inclusion of co-authorships enhances verification decisions in bibliometric environments is experimentally evaluated. Expand
DeepStyle: User Style Embedding for Authorship Attribution of Short Texts
TLDR
This paper proposes DeepStyle, a novel embedding-based framework that learns the representations of users’ salient writing styles, and conducts extensive experiments on two real-world datasets from Twitter and Weibo, showing that DeepStyle outperforms the state-of-the-art baselines on the AA task. Expand
Deep Bayes Factor Scoring for Authorship Verification
TLDR
A hierarchical fusion of two well-known approaches into a single end-to-end learning procedure that incorporates a probabilistic layer to perform Bayes factor scoring in the learned metric space and text preprocessing strategies to deal with the cross-topic issue. Expand
Deep Bayes Factor Scoring for Authorship Verification Notebook for PAN at CLEF 2020
The PAN 2020 authorship verification (AV) challenge focuses on a cross-topic/closed-set AV task over a collection of fanfiction texts. Fanfiction is a fan-written extension of a storyline in which aExpand
The Applicability of Authorship Verification to Swedish Discussion Forums
TLDR
The results are encouraging and show that using AdHominem is a promising way forward when linking user accounts both on the same discussion forum and in cross-domain settings in which users write on a large variety of topics. Expand
Design and Analysis of a Novel Authorship Verification Framework for Hijacked Social Media Accounts Compromised by a Human
TLDR
A novel authorship verification framework for hijacked social media accounts, compromised by a human, is proposed and the ELECTRE approach is utilized for feature selection, and the rank exponent weight method is applied for feature weighting. Expand
(Notebook for PAN at CLEF 2021)
Style change detection focuses on the intrinsic characteristics of a document to determine the location of authorship changes. In this paper, we describe how style change detection can be interpretedExpand
Variational Autoencoder with Embedded Student-t Mixture Model for Authorship Attribution
TLDR
This work is extending a VAE with an embedded Gaussian mixture model to a Student-t mixture model, which allows for an independent control of the “heaviness” of the respective tails of the implied probability densities. Expand
On divergence-based author obfuscation: An attack on the state of the art in statistical authorship verification
TLDR
An approach that models writing style difference as the Jensen-Shannon distance between the character n-gram distributions of texts, and manipulates an author’s writing style in a sophisticated manner using heuristic search is introduced. Expand
Can you fool AI by doing a 180? - A case study on authorship analysis of texts by Arata Osada
TLDR
An attempt at answering a twofold question covering the areas of ethics and authorship analysis solutions: whether it would be possible for an author identification system to correctly attribute works to authors if in the course of years they have undergone a major psychological transition and what it would mean if the authorship attribution system encounters difficulties in detecting single authorship. Expand
...
1
2
...

References

SHOWING 1-10 OF 60 REFERENCES
Similarity Learning for Authorship Verification in Social Media
TLDR
This work proposes a new neural network topology for similarity learning that significantly improves the performance on the author verification task with such challenging data sets. Expand
Learning Stylometric Representations for Authorship Analysis
TLDR
To mimic the human sentence composition process using a neural network approach, it is proposed to incorporate different categories of linguistic features into distributed representation of words in order to learn simultaneously the writing style representations based on unlabeled texts for AA. Expand
A survey of modern authorship attribution methods
TLDR
A survey of recent advances of the automated approaches to attributing authorship is presented, examining their characteristics for both text representation and text classification. Expand
Improving author verification based on topic modeling
TLDR
The comparison to state‐of‐the‐art methods demonstrates the great potential of the approaches presented in this study and demonstrates that even when genre‐agnostic external documents are used, the proposed extrinsic models are very competitive. Expand
Deep Dive into Authorship Verification of Email Messages with Convolutional Neural Network
TLDR
The proposed method implements the binary classification with a sequence-to-sequence (seq2seq) model and trains a convolutional neural network (CNN) on positive and negative examples, and verifies message authorship very accurately. Expand
Authorship verification for different languages, genres and topics
TLDR
A scalable authorship verification method that copes with this problem across different languages, genres and topics and is able to outperform two state-of-the-art baselines, given the same training and test corpora. Expand
A Needle in a Haystack? Harnessing Onomatopoeia and User-specific Stylometrics for Authorship Attribution of Micro-messages
TLDR
By viewing small texts usually employed in social media as unidimensional signals, this work devise modern deep-learning techniques tailored for this kind of data to find the author of these posts with promising results. Expand
Local Histograms of Character N-grams for Authorship Attribution
TLDR
It is shown that LHs are particularly helpful for AA, because they provide useful information for uncovering, to some extent, the writing style of authors for related tasks, such as authorship verification and plagiarism detection. Expand
Authorship Attribution for Social Media Forensics
TLDR
It is argued that there is a significant need in forensics for new authorship attribution algorithms that can exploit context, can process multi-modal data, and are tolerant to incomplete knowledge of the space of all possible authors at training time. Expand
Authorship Attribution and Verification with Many Authors and Limited Data
TLDR
What the effect is of many authors on feature selection and learning, and robustness of a memory-based learning approach in doing authorship attribution and verification with many authors and limited training data when compared to eager learning methods such as SVMs and maximum entropy learning are shown. Expand
...
1
2
3
4
5
...