Detecting Biased Statements in Wikipedia

Hube, Christoph; Fetahu, Besnik

doi:10.1145/3184558.3191640

Cited by 51 publications

(55 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among those who tackle NPOV violations in Wikipedia, some rely on available datasets (Vincze, 2013), others perform manual annotation (Hube and Fetahu, 2018;Ganter and Strube, 2009;Herzig et al, 2011;Al Khatib et al, 2012), still others attempt to automatically extract labeled examples (Ganter and Strube, 2009;Recasens et al, 2013;Hube and Fetahu, 2018). Our approach is in line with the latter.…”

Section: Corporamentioning

confidence: 76%

Multilingual Sentence-Level Bias Detection inWikipedia

Aleksandrova¹,

Lareau²,

Ménard³

2019

Proceedings - Natural Language Processing in a Deep Learning World

View full text Add to dashboard Cite

We propose a multilingual method for the extraction of biased sentences from Wikipedia, and use it to create corpora in Bulgarian, French and English. Sifting through the revision history of the articles that at some point had been considered biased and later corrected, we retrieve the last tagged and the first untagged revisions as the before/after snapshots of what was deemed a violation of Wikipedia's neutral point of view policy. We extract the sentences that were removed or rewritten in that edit. The approach yields sufficient data even in the case of relatively small Wikipedias, such as the Bulgarian one, where 62k articles produced 5k biased sentences. We evaluate our method by manually annotating 520 sentences for Bulgarian and French, and 744 for English. We assess the level of noise and analyze its sources. Finally, we exploit the data with well-known classification methods to detect biased sentences. Code and datasets are hosted at https://github.com/ crim-ca/wiki-bias.

show abstract

Section: Corporamentioning

confidence: 76%

Multilingual Sentence-Level Bias Detection inWikipedia

Aleksandrova¹,

Lareau²,

Ménard³

2019

Proceedings - Natural Language Processing in a Deep Learning World

View full text Add to dashboard Cite

show abstract

“…POS tag are successfully employed in determining text genre [3]. Similarly, POS tags have shown to provide insights in determining biased statements in [15].…”

Section: Statement Representationmentioning

confidence: 99%

“…LIWC Word Functions. LIWC text analysis [20] has been successfully employed in a number of tasks that capture subjectivity of text, such as analyzing language in fake news [22], and additionally as shown in [15], LIWC features when used together with the context of the n-grams proves to provide a high improvement over existing approaches [23] in detecting biased statements.…”

Section: Statement Representationmentioning

confidence: 99%

Neural Based Statement Classification for Biased Language

Hube

Fetahu

2019

Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining

Self Cite

View full text Add to dashboard Cite

Biased language commonly occurs around topics which are of controversial nature, thus, stirring disagreement between the different involved parties of a discussion. This is due to the fact that for language and its use, specifically, the understanding and use of phrases, the stances are cohesive within the particular groups. However, such cohesiveness does not hold across groups.In collaborative environments or environments where impartial language is desired (e.g. Wikipedia, news media), statements and the language therein should represent equally the involved parties and be neutrally phrased. Biased language is introduced through the presence of inflammatory words or phrases, or statements that may be incorrect or one-sided, thus violating such consensus.In this work, we focus on the specific case of phrasing bias, which may be introduced through specific inflammatory words or phrases in a statement. For this purpose, we propose an approach that relies on a recurrent neural networks in order to capture the inter-dependencies between words in a phrase that introduced bias.We perform a thorough experimental evaluation, where we show the advantages of a neural based approach over competitors that rely on word lexicons and other hand-crafted features in detecting biased language. We are able to distinguish biased statements with a precision of P = 0.917, thus significantly outperforming baseline models with an improvement of over 30%. Finally, we release the largest corpus of statements annotated for biased language.

show abstract

“…Despite the domain difference, this task is related to ours because Wikipedia is also a source of information which should contain unbiased language. Systems that were employed for this task used a combination of linguistic features, such as POS n-grams and binary features representing the usage of bias words, assertive verbs, factive verbs, hedges and sentiment features (Recasens et al, 2013;Hube and Fetahu, 2018). Most of these features were derived from existing lexicons.…”

Section: Related Workmentioning

confidence: 99%

“…Nouns frequently provide thematic and topical information about a text and adverbs and adjectives can indicate a level of subjectivity. Modals such as would, could and must could additionally carry assertiveness that could be related to bias (Recasens et al, 2013;Hube and Fetahu, 2018). We tried modelling this by extracting n-grams that followed certain patterns such as a) nouns in the middle of a trigram b) particles in the middle of a trigram c) modal verbs in the middle of a trigram d) nouns and their closest preceding adjectives/adverbs e) adjectives/adverbs and words after them.…”

Section: Pos-based N-gram Filteringmentioning

confidence: 99%

Team Kermit-the-frog at SemEval-2019 Task 4: Bias Detection Through Sentiment Analysis and Simple Linguistic Features

Anthonio¹,

Kloppenburg²

2019

Proceedings of the 13th International Workshop on Semantic Evaluation

View full text Add to dashboard Cite

In this paper we describe our participation in the SemEval 2019 shared task on hyperpartisan news detection. We present the system that we submitted for final evaluation and the three approaches that we used: sentiment, bias-laden words and filtered n-gram features. Our submitted model is a Linear SVM that solely relies on the negative sentiment of a document. We achieved an accuracy of 0.621 and a f1 score of 0.694 in the competition, revealing the predictive power of negative sentiment for this task. There was no major improvement by adding or substituting the features of the other two approaches that we tried.

show abstract

Detecting Biased Statements in Wikipedia

Cited by 51 publications

References 8 publications

Multilingual Sentence-Level Bias Detection inWikipedia

Multilingual Sentence-Level Bias Detection inWikipedia

Neural Based Statement Classification for Biased Language

Team Kermit-the-frog at SemEval-2019 Task 4: Bias Detection Through Sentiment Analysis and Simple Linguistic Features

Contact Info

Product

Resources

About