Truth of Varying Shades: Analyzing Language in Fake News and Political Fact-Checking
01 Sep 2017-pp 2931-2937
TL;DR: Experiments show that while media fact-checking remains to be an open research question, stylistic cues can help determine the truthfulness of text.
Abstract: We present an analytic study on the language of news media in the context of political fact-checking and fake news detection. We compare the language of real news with that of satire, hoaxes, and propaganda to find linguistic characteristics of untrustworthy text. To probe the feasibility of automatic political fact-checking, we also present a case study based on PolitiFact.com using their factuality judgments on a 6-point scale. Experiments show that while media fact-checking remains to be an open research question, stylistic cues can help determine the truthfulness of text.
Citations
More filters
Proceedings Article•
29 May 2019TL;DR: A model for controllable text generation called Grover, found that best current discriminators can classify neural fake news from real, human-written, news with 73% accuracy, assuming access to a moderate level of training data, and the best defense against Grover turns out to be Grover itself, with 92% accuracy.
Abstract: Recent progress in natural language generation has raised dual-use concerns. While applications like summarization and translation are positive, the underlying technology also might enable adversaries to generate neural fake news: targeted propaganda that closely mimics the style of real news. Modern computer security relies on careful threat modeling: identifying potential threats and vulnerabilities from an adversary's point of view, and exploring potential mitigations to these threats. Likewise, developing robust defenses against neural fake news requires us first to carefully investigate and characterize the risks of these models. We thus present a model for controllable text generation called Grover. Given a headline like 'Link Found Between Vaccines and Autism,' Grover can generate the rest of the article; humans find these generations to be more trustworthy than human-written disinformation. Developing robust verification techniques against generators like Grover is critical. We find that best current discriminators can classify neural fake news from real, human-written, news with 73% accuracy, assuming access to a moderate level of training data. Counterintuitively, the best defense against Grover turns out to be Grover itself, with 92% accuracy, demonstrating the importance of public release of strong generators. We investigate these results further, showing that exposure bias -- and sampling strategies that alleviate its effects -- both leave artifacts that similar discriminators can pick up on. We conclude by discussing ethical issues regarding the technology, and plan to release Grover publicly, helping pave the way for better detection of neural fake news.
588 citations
Cites background or methods from "Truth of Varying Shades: Analyzing ..."
...E↵orts to automate fake news detection generally point out stylistic biases that exist in the text (Rashkin et al., 2017; Wang, 2017; Pérez-Rosas et al., 1 We thank past work, such as OpenAI’s Staged Release Policy for GPT2 for drawing attention to neural disinformation, alongside other dual-use…...
[...]
...Efforts to automate fake news detection generally point out stylistic biases that exist in the text (Rashkin et al., 2017; Wang, 2017; Pérez-Rosas et al., 2018)....
[...]
Posted Content•
TL;DR: It is revealed that left-wing and right-wing news share significantly more stylistic similarities than either does with the mainstream, and applications of the results include partisanship detection and pre-screening for semi-automatic fake news detection.
Abstract: This paper reports on a writing style analysis of hyperpartisan (i.e., extremely one-sided) news in connection to fake news. It presents a large corpus of 1,627 articles that were manually fact-checked by professional journalists from BuzzFeed. The articles originated from 9 well-known political publishers, 3 each from the mainstream, the hyperpartisan left-wing, and the hyperpartisan right-wing. In sum, the corpus contains 299 fake news, 97% of which originated from hyperpartisan publishers.
We propose and demonstrate a new way of assessing style similarity between text categories via Unmasking---a meta-learning approach originally devised for authorship verification---, revealing that the style of left-wing and right-wing news have a lot more in common than any of the two have with the mainstream. Furthermore, we show that hyperpartisan news can be discriminated well by its style from the mainstream (F1=0.78), as can be satire from both (F1=0.81). Unsurprisingly, style-based fake news detection does not live up to scratch (F1=0.46). Nevertheless, the former results are important to implement pre-screening for fake news detectors.
375 citations
01 Jul 2018
TL;DR: The authors report on a comparative style analysis of hyperpartisan (extremely one-sided) news and fake news, showing that 97% of the 299 fake news articles identified are also hyperpartisan.
Abstract: We report on a comparative style analysis of hyperpartisan (extremely one-sided) news and fake news. A corpus of 1,627 articles from 9 political publishers, three each from the mainstream, the hyperpartisan left, and the hyperpartisan right, have been fact-checked by professional journalists at BuzzFeed: 97% of the 299 fake news articles identified are also hyperpartisan. We show how a style analysis can distinguish hyperpartisan news from the mainstream (F1 = 0.78), and satire from both (F1 = 0.81). But stylometry is no silver bullet as style-based fake news detection does not work (F1 = 0.46). We further reveal that left-wing and right-wing news share significantly more stylistic similarities than either does with the mainstream. This result is robust: it has been confirmed by three different modeling approaches, one of which employs Unmasking in a novel way. Applications of our results include partisanship detection and pre-screening for semi-automatic fake news detection.
341 citations
TL;DR: This survey describes the modern-day problem of fake news and, in particular, highlights the technical challenges associated with it and comprehensively compile and summarize characteristic features of available datasets.
Abstract: The proliferation of fake news on social media has opened up new directions of research for timely identification and containment of fake news and mitigation of its widespread impact on public opinion. While much of the earlier research was focused on identification of fake news based on its contents or by exploiting users’ engagements with the news on social media, there has been a rising interest in proactive intervention strategies to counter the spread of misinformation and its impact on society. In this survey, we describe the modern-day problem of fake news and, in particular, highlight the technical challenges associated with it. We discuss existing methods and techniques applicable to both identification and mitigation, with a focus on the significant advances in each method and their advantages and limitations. In addition, research has often been limited by the quality of existing datasets and their specific application contexts. To alleviate this problem, we comprehensively compile and summarize characteristic features of available datasets. Furthermore, we outline new directions of research to facilitate future development of effective and interdisciplinary solutions.
280 citations
Cites background from "Truth of Varying Shades: Analyzing ..."
...A specific variant called Long Short-TermMemory (LSTM) [42], which alleviates some of the training difficulties in RNN, is often used due to the its ability to effectively capture long-range dependencies in the text and has been applied to fake news detection, similarly to the use of convolutional neural networks in several works [91, 117]....
[...]
Posted Content•
TL;DR: A novel automatic fake news detection model based on geometric deep learning that can be reliably detected at an early stage, after just a few hours of propagation, and the results point to the promise of propagation-based approaches forfake news detection as an alternative or complementary strategy to content-based approach.
Abstract: Social media are nowadays one of the main news sources for millions of people around the globe due to their low cost, easy access and rapid dissemination. This however comes at the cost of dubious trustworthiness and significant risk of exposure to 'fake news', intentionally written to mislead the readers. Automatically detecting fake news poses challenges that defy existing content-based analysis approaches. One of the main reasons is that often the interpretation of the news requires the knowledge of political or social context or 'common sense', which current NLP algorithms are still missing. Recent studies have shown that fake and real news spread differently on social media, forming propagation patterns that could be harnessed for the automatic fake news detection. Propagation-based approaches have multiple advantages compared to their content-based counterparts, among which is language independence and better resilience to adversarial attacks. In this paper we show a novel automatic fake news detection model based on geometric deep learning. The underlying core algorithms are a generalization of classical CNNs to graphs, allowing the fusion of heterogeneous data such as content, user profile and activity, social graph, and news propagation. Our model was trained and tested on news stories, verified by professional fact-checking organizations, that were spread on Twitter. Our experiments indicate that social network structure and propagation are important features allowing highly accurate (92.7% ROC AUC) fake news detection. Second, we observe that fake news can be reliably detected at an early stage, after just a few hours of propagation. Third, we test the aging of our model on training and testing data separated in time. Our results point to the promise of propagation-based approaches for fake news detection as an alternative or complementary strategy to content-based approaches.
280 citations
Cites background from "Truth of Varying Shades: Analyzing ..."
...Content-based approaches, which are used in the majority of works on fake news detection, rely on linguistic (lexical and syntactical) features that can capture deceptive cues or writing styles [1, 32, 30, 29, 28]....
[...]
References
More filters
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Abstract: Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O. 1. Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.
72,897 citations
01 Oct 2014
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Abstract: Recent methods for learning vector space representations of words have succeeded in capturing fine-grained semantic and syntactic regularities using vector arithmetic, but the origin of these regularities has remained opaque. We analyze and make explicit the model properties needed for such regularities to emerge in word vectors. The result is a new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods. Our model efficiently leverages statistical information by training only on the nonzero elements in a word-word cooccurrence matrix, rather than on the entire sparse matrix or on individual context windows in a large corpus. The model produces a vector space with meaningful substructure, as evidenced by its performance of 75% on a recent word analogy task. It also outperforms related models on similarity tasks and named entity recognition.
30,558 citations
"Truth of Varying Shades: Analyzing ..." refers methods in this paper
...The LSTM word embeddings are initialized with 100-dim embeddings from GLOVE (Pennington et al., 2014) and fine-tuned during training....
[...]
TL;DR: In this paper, subjects supporting and opposing capital punishment were exposed to two purported studies, one seemingly confirming and one seemingly disconfirming their existing beliefs about the deterrent efficacy of the death penalty.
Abstract: People who hold strong opinions on complex social issues are likely to examine relevant empirical evidence in a biased manner. They are apt to accept "confirming" evidence at face value while subjecting "discontinuing" evidence to critical evaluation, and as a result to draw undue support for their initial positions from mixed or random empirical findings. Thus, the result of exposing contending factions in a social dispute to an identical body of relevant empirical evidence may be not a narrowing of disagreement but rather an increase in polarization. To test these assumptions and predictions, subjects supporting and opposing capital punishment were exposed to two purported studies, one seemingly confirming and one seemingly disconfirming their existing beliefs about the deterrent efficacy of the death penalty. As predicted, both proponents and opponents of capital punishment rated those results and procedures that confirmed their own beliefs to be the more convincing and probative ones, and they reported corresponding shifts in their beliefs as the various results and procedures were presented. The net effect of such evaluations and opinion shifts was the postulated increase in attitude polarization. The human understanding when it has once adopted an opinion draws all things else to support and agree with it. And though there be a greater number and weight of instances to be found on the other side, yet these it either neglects and despises, or else by some distinction sets aside and rejects, in order that by this great and pernicious predetermination the authority of its former conclusion may remain inviolate. (Bacon, 1620/1960)
3,808 citations
"Truth of Varying Shades: Analyzing ..." refers background in this paper
...Fact-Checking and Fake News There is research in political science exploring how effective fact-checking is at improving people’s awareness (Lord et al., 1979; Thorson, 2016; Nyhan and Reifler, 2015)....
[...]
...Fact-Checking and Fake News There is research in political science exploring how effective fact-checking is at improving people’s awareness (Lord et al., 1979; Thorson, 2016; Nyhan and Reifler, 2015)....
[...]
06 Oct 2005
TL;DR: A new approach to phrase-level sentiment analysis is presented that first determines whether an expression is neutral or polar and then disambiguates the polarity of the polar expressions.
Abstract: This paper presents a new approach to phrase-level sentiment analysis that first determines whether an expression is neutral or polar and then disambiguates the polarity of the polar expressions. With this approach, the system is able to automatically identify the contextual polarity for a large subset of sentiment expressions, achieving results that are significantly better than baseline.
3,433 citations
"Truth of Varying Shades: Analyzing ..." refers background or methods in this paper
...and weakly subjective words with a sentiment lexicon (Wilson et al., 2005)....
[...]
...In addition, we estimate the use of strongly and weakly subjective words with a sentiment lexicon (Wilson et al., 2005)....
[...]
Book•
12 Jun 2009TL;DR: This book offers a highly accessible introduction to natural language processing, the field that supports a variety of language technologies, from predictive text and email filtering to automatic summarization and translation.
Abstract: This book offers a highly accessible introduction to natural language processing, the field that supports a variety of language technologies, from predictive text and email filtering to automatic summarization and translation. With it, you'll learn how to write Python programs that work with large collections of unstructured text. You'll access richly annotated datasets using a comprehensive range of linguistic data structures, and you'll understand the main algorithms for analyzing the content and structure of written communication. Packed with examples and exercises, Natural Language Processing with Python will help you: Extract information from unstructured text, either to guess the topic or identify "named entities" Analyze linguistic structure in text, including parsing and semantic analysis Access popular linguistic databases, including WordNet and treebanks Integrate techniques drawn from fields as diverse as linguistics and artificial intelligence This book will help you gain practical skills in natural language processing using the Python programming language and the Natural Language Toolkit (NLTK) open source library. If you're interested in developing web applications, analyzing multilingual news sources, or documenting endangered languages -- or if you're simply curious to have a programmer's perspective on how human language works -- you'll find Natural Language Processing with Python both fascinating and immensely useful.
3,361 citations
"Truth of Varying Shades: Analyzing ..." refers background or methods in this paper
...the text with NLTK (Bird et al., 2009) and compute per-document count for each lexicon, and report averages per article of each type....
[...]
...We tokenize 2All resources created for this paper including corpus of news articles from unreliable sources, collection of Politifact ratings, and compiled Wiktionary lexicons have been made publicly available at homes.cs.washington. edu/˜hrashkin/factcheck.html 3www.usnews.com/news/national-news/articles/2016-1114/avoid-these-fake-news-sites-at-all-costs the text with NLTK (Bird et al., 2009) and compute per-document count for each lexicon, and report averages per article of each type....
[...]
...…available at homes.cs.washington. edu/˜hrashkin/factcheck.html 3www.usnews.com/news/national-news/articles/2016-1114/avoid-these-fake-news-sites-at-all-costs the text with NLTK (Bird et al., 2009) and compute per-document count for each lexicon, and report averages per article of each type....
[...]