Coordinated inauthentic behavior is used as a tool on social media to shape public opinion by elevating or suppressing topics using systematic engagements -- e.g. through *likes* or similar reactions. In an honest world, reactions may be informative to users when selecting on what to spend their attention: through the wisdom of crowds, summed reactions may help identifying relevant and high-quality content. This is nullified by coordinated inauthentic liking. To restore wisdom-of-crowds effects, it is therefore desirable to separate the inauthentic agents from the wise crowd, and use only the latter as a voting *jury* on the relevance of a post. To this end, we design two *jury selection procedures* (JSPs) that discard agents classified as inauthentic. Using machine learning techniques, both cluster on binary vote data -- one using a Gaussian Mixture Model (GMM JSP), one the k-means algorithm (KM JSP) -- and label agents by logistic regression. We evaluate the jury selection procedures with an agent-based model, and show that the GMM JSP detects more inauthentic agents, but both JSPs select juries with vastly increased correctness of vote by majority. This proof of concept provides an argument for the release of reactions data from social media platforms through a direct use-case in the fight against online misinformation.
相關內容
This paper describes our participation in the MentalRiskES task at IberLEF 2023. The task involved predicting the likelihood of an individual experiencing depression based on their social media activity. The dataset consisted of conversations from 175 Telegram users, each labeled according to their evidence of suffering from the disorder. We used a combination of traditional machine learning and deep learning techniques to solve four predictive subtasks: binary classification, simple regression, multiclass classification, and multiclass regression. We approached this by training a model to solve the multiclass regression case and then transforming the predictions to work for the other three subtasks. We compare the performance of two different modeling approaches: fine-tuning a BERT-based model and using sentence embeddings as inputs to a linear regressor, with the latter yielding better results. The code to reproduce our results can be found at: //github.com/simonsanvil/EarlyDepression-MentalRiskES.
Financial stability is a key challenge for individuals with bipolar disorder, a serious mental illness requiring life-long management. Symptomatic periods often lead to poor financial decision-making, including compulsive spending and risky behaviors. Widespread consumer adoption of financial technologies ("fintech") has accelerated in recent years, with numerous consumer-centric applications providing insight into personal financial behavior in exchange for access to financial data. We believe these technologies can be applied to meaningfully support individual resilience in this population and, potentially, the resilience of families and surrounding networks of care. However, little is known about this population's unique perspectives, expectations, or privacy preferences related to financial data sharing for these purposes. To this end, we deployed an online survey (N=480) to assess the privacy expectations of individuals with bipolar disorder surrounding the use of financial data as an early-warning indicator of symptoms. A factorial vignette design allowed us to vary vignette dimensions across the granularity of financial data types, context of potential data use, and recipient of data insights. This exploratory analysis demonstrates that individuals are most comfortable sharing financial data when they were the only party to receive algorithmically-generated insights, while factors such as context of use and granularity of data types were less significant. Individuals who were most willing to engage creditors or other financial technologies for assistance were significantly more willing to share with family members and clinicians.
The increasing prevalence of Artificial Intelligence (AI) in safety-critical contexts such as air-traffic control leads to systems that are practical and efficient, and to some extent explainable to humans to be trusted and accepted. The present structured literature analysis examines n = 236 articles on the requirements for the explainability and acceptance of AI. Results include a comprehensive review of n = 48 articles on information people need to perceive an AI as explainable, the information needed to accept an AI, and representation and interaction methods promoting trust in an AI. Results indicate that the two main groups of users are developers who require information about the internal operations of the model and end users who require information about AI results or behavior. Users' information needs vary in specificity, complexity, and urgency and must consider context, domain knowledge, and the user's cognitive resources. The acceptance of AI systems depends on information about the system's functions and performance, privacy and ethical considerations, as well as goal-supporting information tailored to individual preferences and information to establish trust in the system. Information about the system's limitations and potential failures can increase acceptance and trust. Trusted interaction methods are human-like, including natural language, speech, text, and visual representations such as graphs, charts, and animations. Our results have significant implications for future human-centric AI systems being developed. Thus, they are suitable as input for further application-specific investigations of user needs.
Context. Algorithmic racism is the term used to describe the behavior of technological solutions that constrains users based on their ethnicity. Lately, various data-driven software systems have been reported to discriminate against Black people, either for the use of biased data sets or due to the prejudice propagated by software professionals in their code. As a result, Black people are experiencing disadvantages in accessing technology-based services, such as housing, banking, and law enforcement. Goal. This study aims to explore algorithmic racism from the perspective of software professionals. Method. A survey questionnaire was applied to explore the understanding of software practitioners on algorithmic racism, and data analysis was conducted using descriptive statistics and coding techniques. Results. We obtained answers from a sample of 73 software professionals discussing their understanding and perspectives on algorithmic racism in software development. Our results demonstrate that the effects of algorithmic racism are well-known among practitioners. However, there is no consensus on how the problem can be effectively addressed in software engineering. In this paper, some solutions to the problem are proposed based on the professionals' narratives. Conclusion. Combining technical and social strategies, including training on structural racism for software professionals, is the most promising way to address the algorithmic racism problem and its effects on the software solutions delivered to our society.
Art forms such as movies and television (TV) dramas are reflections of the real world, which have attracted much attention from the multimodal learning community recently. However, existing corpora in this domain share three limitations: (1) annotated in a scene-oriented fashion, they ignore the coherence within plots; (2) their text lacks empathy and seldom mentions situational context; (3) their video clips fail to cover long-form relationship due to short duration. To address these fundamental issues, using 1,106 TV drama episodes and 24,875 informative plot-focused sentences written by professionals, with the help of 449 human annotators, we constructed PTVD, the first plot-oriented multimodal dataset in the TV domain. It is also the first non-English dataset of its kind. Additionally, PTVD contains more than 26 million bullet screen comments (BSCs), powering large-scale pre-training. Next, aiming to open-source a strong baseline for follow-up works, we developed the multimodal algorithm that attacks different cinema/TV modelling problems with a unified architecture. Extensive experiments on three cognitive-inspired tasks yielded a number of novel observations (some of them being quite counter-intuition), further validating the value of PTVD in promoting multimodal research. The dataset and codes are released at \url{//ptvd.github.io/}.
Nowadays, containerized freight transport is one of the most important transportation systems that is undergoing an automation process due to the Deep Learning success. However, it suffers from a lack of annotated data in order to incorporate state-of-the-art neural network models to its systems. In this paper we present an innovative methodology to generate a realistic, varied, balanced, and labelled dataset for visual inspection task of containers in a dock environment. In addition, we validate this methodology with multiple visual tasks recurrently found in the state of the art. We prove that the generated synthetic labelled dataset allows to train a deep neural network that can be used in a real world scenario. On the other side, using this methodology we provide the first open synthetic labelled dataset called SeaFront available in: //datasets.vicomtech.org/di21-seafront/readme.txt.
The rise in adoption of cryptoassets has brought many new and inexperienced investors in the cryptocurrency space. These investors can be disproportionally influenced by information they receive online, and particularly from social media. This paper presents a dataset of crypto-related bounty events and the users that participate in them. These events coordinate social media campaigns to create artificial "hype" around a crypto project in order to influence the price of its token. The dataset consists of information about 15.8K cross-media bounty events, 185K participants, 10M forum comments and 82M social media URLs collected from the Bounties(Altcoins) subforum of the BitcoinTalk online forum from May 2014 to December 2022. We describe the data collection and the data processing methods employed and we present a basic characterization of the dataset. Furthermore, we discuss potential research opportunities afforded by the dataset across many disciplines and we highlight potential novel insights into how the cryptocurrency industry operates and how it interacts with its audience.
Recent advances in generative pre-trained transformer large language models have emphasised the potential risks of unfair use of artificial intelligence (AI) generated content in an academic environment and intensified efforts in searching for solutions to detect such content. The paper examines the general functionality of detection tools for artificial intelligence generated text and evaluates them based on accuracy and error type analysis. Specifically, the study seeks to answer research questions about whether existing detection tools can reliably differentiate between human-written text and ChatGPT-generated text, and whether machine translation and content obfuscation techniques affect the detection of AIgenerated text. The research covers 12 publicly available tools and two commercial systems (Turnitin and PlagiarismCheck) that are widely used in the academic setting. The researchers conclude that the available detection tools are neither accurate nor reliable and have a main bias towards classifying the output as human-written rather than detecting AIgenerated text. Furthermore, content obfuscation techniques significantly worsen the performance of tools. The study makes several significant contributions. First, it summarises up-to-date similar scientific and non-scientific efforts in the field. Second, it presents the result of one of the most comprehensive tests conducted so far, based on a rigorous research methodology, an original document set, and a broad coverage of tools. Third, it discusses the implications and drawbacks of using detection tools for AI-generated text in academic settings.
In recent years, Graph Neural Networks have reported outstanding performance in tasks like community detection, molecule classification and link prediction. However, the black-box nature of these models prevents their application in domains like health and finance, where understanding the models' decisions is essential. Counterfactual Explanations (CE) provide these understandings through examples. Moreover, the literature on CE is flourishing with novel explanation methods which are tailored to graph learning. In this survey, we analyse the existing Graph Counterfactual Explanation methods, by providing the reader with an organisation of the literature according to a uniform formal notation for definitions, datasets, and metrics, thus, simplifying potential comparisons w.r.t to the method advantages and disadvantages. We discussed seven methods and sixteen synthetic and real datasets providing details on the possible generation strategies. We highlight the most common evaluation strategies and formalise nine of the metrics used in the literature. We first introduce the evaluation framework GRETEL and how it is possible to extend and use it while providing a further dimension of comparison encompassing reproducibility aspects. Finally, we provide a discussion on how counterfactual explanation interplays with privacy and fairness, before delving into open challenges and future works.
Decision-making algorithms are being used in important decisions, such as who should be enrolled in health care programs and be hired. Even though these systems are currently deployed in high-stakes scenarios, many of them cannot explain their decisions. This limitation has prompted the Explainable Artificial Intelligence (XAI) initiative, which aims to make algorithms explainable to comply with legal requirements, promote trust, and maintain accountability. This paper questions whether and to what extent explainability can help solve the responsibility issues posed by autonomous AI systems. We suggest that XAI systems that provide post-hoc explanations could be seen as blameworthy agents, obscuring the responsibility of developers in the decision-making process. Furthermore, we argue that XAI could result in incorrect attributions of responsibility to vulnerable stakeholders, such as those who are subjected to algorithmic decisions (i.e., patients), due to a misguided perception that they have control over explainable algorithms. This conflict between explainability and accountability can be exacerbated if designers choose to use algorithms and patients as moral and legal scapegoats. We conclude with a set of recommendations for how to approach this tension in the socio-technical process of algorithmic decision-making and a defense of hard regulation to prevent designers from escaping responsibility.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191