Search Results for author: Daniel Preo{\c{t}}iuc-Pietro

Found 24 papers, 2 papers with code

Categorizing and Inferring the Relationship between the Text and Image of Twitter Posts

no code implementations ACL 2019 Alakan Vempala, a, Daniel Preo{\c{t}}iuc-Pietro

We show that by combining the text and image information, we can build a machine learning approach that accurately distinguishes between the relationship types.

Image Captioning

Analyzing Linguistic Differences between Owner and Staff Attributed Tweets

1 code implementation ACL 2019 Daniel Preo{\c{t}}iuc-Pietro, Rita Devlin Marier

Research on social media has to date assumed that all posts from an account are authored by the same person.

Why Swear? Analyzing and Inferring the Intentions of Vulgar Expressions

no code implementations EMNLP 2018 Eric Holgate, Isabel Cachola, Daniel Preo{\c{t}}iuc-Pietro, Junyi Jessy Li

Vulgar words are employed in language use for several different functions, ranging from expressing aggression to signaling group identity or the informality of the communication.

Hate Speech Detection

User-Level Race and Ethnicity Predictors from Twitter Text

no code implementations COLING 2018 Daniel Preo{\c{t}}iuc-Pietro, Lyle Ungar

User demographic inference from social media text has the potential to improve a range of downstream applications, including real-time passive polling or quantifying demographic bias.

Beyond Binary Labels: Political Ideology Prediction of Twitter Users

no code implementations ACL 2017 Daniel Preo{\c{t}}iuc-Pietro, Ye Liu, Daniel Hopkins, Lyle Ungar

Automatic political orientation prediction from social media posts has to date proven successful only in distinguishing between publicly declared liberals and conservatives in the US.

Predicting Emotional Word Ratings using Distributional Representations and Signed Clustering

no code implementations EACL 2017 Jo{\~a}o Sedoc, Daniel Preo{\c{t}}iuc-Pietro, Lyle Ungar

Inferring the emotional content of words is important for text-based sentiment analysis, dialogue systems and psycholinguistics, but word ratings are expensive to collect at scale and across languages or domains.

Clustering Position +2

Cannot find the paper you are looking for? You can Submit a new open access paper.