Open AccessProceedings Article
Linguistic Models for Analyzing and Detecting Biased Language
Marta Recasens,Cristian Danescu-Niculescu-Mizil,Dan Jurafsky +2 more
- pp 1650-1659
TLDR
The analysis of real instances of human edits designed to remove bias from Wikipedia articles uncovers two classes of bias: framing bias, such as praising or perspective-specific words, which is linked to the literature on subjectivity; and epistemological bias, related to whether propositions that are presupposed or entailed in the text are uncontroversially accepted as true.Abstract:
Unbiased language is a requirement for reference sources like encyclopedias and scientific texts. Bias is, nonetheless, ubiquitous, making it crucial to understand its nature and linguistic realization and hence detect bias automatically. To this end we analyze real instances of human edits designed to remove bias from Wikipedia articles. The analysis uncovers two classes of bias: framing bias, such as praising or perspective-specific words, which we link to the literature on subjectivity; and epistemological bias, related to whether propositions that are presupposed or entailed in the text are uncontroversially accepted as true. We identify common linguistic cues for these classes, including factive verbs, implicatives, hedges, and subjective intensifiers. These insights help us develop features for a model to solve a new prediction task of practical importance: given a biased sentence, identify the bias-inducing word. Our linguistically-informed model performs almost as well as humans tested on the same task.read more
Citations
More filters
Proceedings ArticleDOI
Truth of Varying Shades: Analyzing Language in Fake News and Political Fact-Checking
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.
Proceedings ArticleDOI
Delete, retrieve, generate: A simple approach to sentiment and style transfer
TL;DR: This paper proposed simpler methods motivated by the observation that text attributes are often marked by distinctive phrases (e.g., “too small”) and used a neural model to fluently combine these into a final output.
Posted Content
Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer
TL;DR: This paper proposes simpler methods motivated by the observation that text attributes are often marked by distinctive phrases, and the strongest method extracts content words by deleting phrases associated with the sentence’s original attribute value, retrieves new phrases associatedwith the target attribute, and uses a neural model to fluently combine these into a final output.
Proceedings ArticleDOI
Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter
TL;DR: This work builds predictive models to classify 130 thousand news posts as suspicious or verified, and predict four sub-types of suspicious news – satire, hoaxes, clickbait and propaganda, and shows that neural network models trained on tweet content and social network interactions outperform lexical models.
Posted Content
Stance and Sentiment in Tweets
TL;DR: It is shown that although knowing the sentiment expressed by a tweet is beneficial for stance classification, it alone is not sufficient and additional unlabeled data is used through distant supervision techniques and word embeddings to further improve stance classification.
References
More filters
Posted Content
Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews
TL;DR: A simple unsupervised learning algorithm for classifying reviews as recommended (thumbs up) or not recommended (Thumbs down) if the average semantic orientation of its phrases is positive.
Proceedings Article
Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews
TL;DR: This article proposed an unsupervised learning algorithm for classifying reviews as recommended (thumbs up) or not recommended(thumbs down) based on the average semantic orientation of phrases in the review that contain adjectives or adverbs.
Proceedings Article
Generating Typed Dependency Parses from Phrase Structure Parses
TL;DR: A system for extracting typed dependency parses of English sentences from phrase structure parses that captures inherent relations occurring in corpus texts that can be critical in real-world applications is described.
Proceedings ArticleDOI
Opinion observer: analyzing and comparing opinions on the Web
TL;DR: A novel framework for analyzing and comparing consumer opinions of competing products is proposed, and a new technique based on language pattern mining is proposed to extract product features from Pros and Cons in a particular type of reviews.
Journal ArticleDOI
Framing Bias: Media in the Distribution of Power
TL;DR: This paper integrated the insights generated by framing, priming, and agenda-setting research through a systematic effort to conceptualize and understand their larger implications for political power and democracy, and proposed improved measures of slant and bias.