{"title":"Sequential Classification of Misinformation","authors":"Daniel Toma, Wasim Huleihel","doi":"arxiv-2409.04860","DOIUrl":null,"url":null,"abstract":"In recent years there have been a growing interest in online auditing of\ninformation flow over social networks with the goal of monitoring undesirable\neffects, such as, misinformation and fake news. Most previous work on the\nsubject, focus on the binary classification problem of classifying information\nas fake or genuine. Nonetheless, in many practical scenarios, the\nmulti-class/label setting is of particular importance. For example, it could be\nthe case that a social media platform may want to distinguish between ``true\",\n``partly-true\", and ``false\" information. Accordingly, in this paper, we\nconsider the problem of online multiclass classification of information flow.\nTo that end, driven by empirical studies on information flow over real-world\nsocial media networks, we propose a probabilistic information flow model over\ngraphs. Then, the learning task is to detect the label of the information flow,\nwith the goal of minimizing a combination of the classification error and the\ndetection time. For this problem, we propose two detection algorithms; the\nfirst is based on the well-known multiple sequential probability ratio test,\nwhile the second is a novel graph neural network based sequential decision\nalgorithm. For both algorithms, we prove several strong statistical guarantees.\nWe also construct a data driven algorithm for learning the proposed\nprobabilistic model. Finally, we test our algorithms over two real-world\ndatasets, and show that they outperform other state-of-the-art misinformation\ndetection algorithms, in terms of detection time and classification error.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Social and Information Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.04860","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In recent years there have been a growing interest in online auditing of
information flow over social networks with the goal of monitoring undesirable
effects, such as, misinformation and fake news. Most previous work on the
subject, focus on the binary classification problem of classifying information
as fake or genuine. Nonetheless, in many practical scenarios, the
multi-class/label setting is of particular importance. For example, it could be
the case that a social media platform may want to distinguish between ``true",
``partly-true", and ``false" information. Accordingly, in this paper, we
consider the problem of online multiclass classification of information flow.
To that end, driven by empirical studies on information flow over real-world
social media networks, we propose a probabilistic information flow model over
graphs. Then, the learning task is to detect the label of the information flow,
with the goal of minimizing a combination of the classification error and the
detection time. For this problem, we propose two detection algorithms; the
first is based on the well-known multiple sequential probability ratio test,
while the second is a novel graph neural network based sequential decision
algorithm. For both algorithms, we prove several strong statistical guarantees.
We also construct a data driven algorithm for learning the proposed
probabilistic model. Finally, we test our algorithms over two real-world
datasets, and show that they outperform other state-of-the-art misinformation
detection algorithms, in terms of detection time and classification error.