The world is facing a new era in which social media communication plays a fundamental role in people’s lives. Along with proven benefits, several collateral drawbacks have risen, one being the widespread of false information with malicious intents, oftentimes using anonymous or false identities. Fighting this problem is challenging, especially when considering the nature of text messages involved on social media platforms: a sea of small messages and a myriad of users. Attributing the authorship of such messages is an ambitious endeavor; nevertheless, it is a way to fight this undesired disinformation scenario. In this work, we tackle the problem of authorship attribution of tiny messages, but, different from what has been done with longer texts, we rely upon data-driven approaches, avoiding handcraft features and harnessing recent advances of deep neural networks in the field of pattern recognition. By modeling small texts employed in social media as unidimensional signals, we propose a deep learning model to project these messages onto a manifold suitable for the task of authorship attribution. We provide two state-of-the-art solutions tailored for different setups and strategies for the scenario of authorship verification. These advances were possible, thanks to three additional contributions: an updated dataset based on the Twitter® platform, new sanitization techniques to improve the quality of the training data, and novel visual analytics techniques to help the development of authorship attribution solutions.

Learning from fully-unlabeled data is challenging in Multimedia Forensics problems, such as Person Re-Identification and Text Authorship Attribution. Recent self-supervised learning methods have shown to be effective when dealing with fully-unlabeled data in cases where the underlying classes have significant semantic differences, as intra-class distances are substantially lower than inter-class distances. However, this is not the case for forensic applications in which classes have similar semantics and the training and test sets have disjoint identities. General self-supervised learning methods might fail to learn discriminative features in this scenario, thus requiring more robust strategies. We propose a strategy to tackle Person Re-Identification and Text Authorship Attribution by enabling learning from unlabeled data even when samples from different classes are not prominently diverse. We propose a novel ensemble-based clustering strategy whereby clusters derived from different configurations are combined to generate a better grouping for the data samples in a fully-unsupervised way. This strategy allows clusters with different densities and higher variability to emerge, reducing intra-class discrepancies without requiring the burden of finding an optimal configuration per dataset. We also consider different Convolutional Neural Networks for feature extraction and subsequent distance computations between samples. We refine these distances by incorporating context and grouping them to capture complementary information. Our method is robust across both tasks, with different data modalities, and outperforms state-of-the-art methods with a fully-unsupervised solution without any labeling or human intervention.

One of the major modern threats to society is the propagation of misinformation — fake news, science denialism, hate speech — fueled by social media’s widespread adoption. On the leading social platforms, millions of automated and fake profiles exist only for this purpose. One step to mitigate this problem is verifying the authenticity of profiles, which proves to be an infeasible task to be done manually. Recent data-driven methods accurately tackle this problem by performing automatic authorship attribution, although an important aspect is often overlooked: model interpretability. Is it possible to make the decision process of such methods transparent and interpretable for social media content considering its specificities? In this work, we extend upon LIME — a model-agnostic interpretability technique — to improve the explanations of the state-of-the-art methods for authorship attribution on social media posts. Our extension allows us to employ the same input representation of the model as interpretable features, identifying important elements for the authorship process. We also allow coping with the lack of perturbed samples in the scenario of short messages. Finally, we show qualitative and quantitative evidence of these findings.

In the last few years, social media networks have changed human life experience and behavior as it has broken down communication barriers, allowing ordinary people to actively produce multimedia content on a massive scale. On this wise, the information dissemination in social media platforms becomes increasingly common. However, misinformation is propagated with the same facility and velocity as real news, though it can result in irreversible damage to an individual or society at large. Solving this problem is not a trivial task, considering the reduced size of the text messages usually posted on these communication vehicles. This paper proposes an end-to-end framework called EMET to classify the reliability of small messages posted on social media platforms. Our method leverages text-embeddings from multilingual-encoder transformers that take into consideration the semantic knowledge from preceding trustworthy news and the use of the reader's reactions to detect misleading content. Our findings demonstrated the value of user interaction and prior information to check social media post's credibility.

The world is facing a new era in which social media communication plays a fundamental role in people's lives. Along with irrefutable benefits, several collateral drawbacks have risen, one being the wide spread of false information with malicious intents, what is now commonly called "Fake News". The fight against this problem is not easy, especially when taking into account the nature of text messages involved on social media platforms (a sea of small messages and myriad users). In this work, we cope with the challenging problem of authorship attribution of small text messages posted on social media platforms. Differently from what has been done with longer texts, we rely upon data-driven approaches, exploiting recent advances of deep neural networks in the field of pattern recognition. By viewing small texts usually employed in social media as unidimensional signals, we devise modern deep-learning techniques tailored for this kind of data to find the author of these posts with promising results.

The veil of anonymity provided by smartphones with pre-paid SIM cards, public Wi-Fi hotspots, and distributed networks like Tor has drastically complicated the task of identifying users of social media during forensic investigations. In some cases, the text of a single posted message will be the only clue to an author's identity. How can we accurately predict who that author might be when the message may never exceed 140 characters on a service like Twitter? For the past 50 years, linguists, computer scientists, and scholars of the humanities have been jointly developing automated methods to identify authors based on the style of their writing. All authors possess peculiarities of habit that influence the form and content of their written works. These characteristics can often be quantified and measured using machine learning algorithms. In this paper, we provide a comprehensive review of the methods of authorship attribution that can be applied to the problem of social media forensics. Furthermore, we examine emerging supervised learning-based methods that are effective for small sample sizes, and provide step-by-step explanations for several scalable approaches as instructional case studies for newcomers to the field. We argue 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.