Research Data Leeds Repository

Headlines data for social media popularity prediction

Piotrkowicz, Alicja (2017) Headlines data for social media popularity prediction. University of Leeds. [Dataset] https://doi.org/10.5518/174

Dataset description

This dataset is part of a larger project on using headlines to predict the social media popularity of news articles. The dataset consists of two headlines corpora -- The Guardian and New York Times -- collected in 2014 using news outlet APIs. Each corpus includes a unique headline identifier (to enable recreating the corpus by querying the relevant API), the extracted features (news values, style, metadata), and the corresponding popularity on Twitter and Facebook.

Keywords:	headlines, news values, style, social media popularity, prediction from text
Subjects:	I000 - Computer sciences > I400 - Artificial intelligence > I410 - Speech & natural language processing
Divisions:	Faculty of Engineering and Physical Sciences > School of Computing
Related resources:	Location Type http://eprints.whiterose.ac.uk/115200/ Publication http://eprints.whiterose.ac.uk/115024/ Publication http://etheses.whiterose.ac.uk/20430/ Publication
License:	Creative Commons Attribution 4.0 International (CC BY 4.0)
Date deposited:	11 May 2017 09:50
URI:	http://archive.researchdata.leeds.ac.uk/id/eprint/147
Additional details Additional details Creators: Creators ORCID Other ID Email Primary affiliation Primary affiliation ID Primary affiliation ID type Secondary affiliation Secondary affiliation ID Secondary affiliation ID type Piotrkowicz, Alicja https://orcid.org/0000-0002-7723-699X Type of data: Dataset Contributors: Contribution Name ORCID Other ID Email Primary affiliation Primary affiliation ID Primary affiliation ID type Secondary affiliation Secondary affiliation ID Secondary affiliation ID type Supervisor Dimitrova, Vania https://orcid.org/0000-0002-7001-0891 Research funders: EPSRC Grant numbers: Doctoral Training Grant Publication date: 2017 Resource language: English Metadata language: English Publisher: University of Leeds Contact Email Address: scap@leeds.ac.uk Last Modified: 08 Jun 2018 12:08

Files

Documentation

Dataset description [120kB] Dataset description [120kB] Dataset description [120kB] Visible to: Anyone File name: readme.pdf Content type: Documentation Mime-Type: application/pdf File size: 120kB

Data

Feature vectors for the main model (The Guardian) [2MB] Feature vectors for the main model (The Guardian) [2MB] Feature vectors for the main model (The Guardian) [2MB] Visible to: Anyone File name: guardian_main_model.zip Content type: Data Description: Headlines from The Guardian with extracted features (news values, style, metadata), divided into training and test sets Mime-Type: application/zip File size: 2MB

Feature vectors for the main model (New York Times) [508kB] Feature vectors for the main model (New York Times) [508kB] Feature vectors for the main model (New York Times) [508kB] Visible to: Anyone File name: nyt_main_model.zip Content type: Data Description: Headlines from New York Times with extracted features (news values, style, metadata), divided into training and test sets Mime-Type: application/zip File size: 508kB

Popularity measures (The Guardian) [663kB] Popularity measures (The Guardian) [663kB] Popularity measures (The Guardian) [663kB] Visible to: Anyone File name: guardian_popularity_measures.zip Content type: Data Description: Headlines from The Guardian with their social media popularity measures, divided into training and test sets Mime-Type: application/zip File size: 663kB

Popularity measures (New York Times) [94kB] Popularity measures (New York Times) [94kB] Popularity measures (New York Times) [94kB] Visible to: Anyone File name: nyt_popularity_measures.zip Content type: Data Description: Headlines from New York Times with their social media popularity measures, divided into training and test sets Mime-Type: application/zip File size: 94kB

Feature vectors for the baseline models (The Guardian) [3MB] Feature vectors for the baseline models (The Guardian) [3MB] Feature vectors for the baseline models (The Guardian) [3MB] Visible to: Anyone File name: guardian_baseline_models.zip Content type: Data Description: Headlines from The Guardian with extracted baselines features, divided into training and test sets Mime-Type: application/zip File size: 3MB

Feature vectors for the baseline models (New York Times) [629kB] Feature vectors for the baseline models (New York Times) [629kB] Feature vectors for the baseline models (New York Times) [629kB] Visible to: Anyone File name: nyt_baseline_models.zip Content type: Data Description: Headlines from New York Times with extracted baselines features, divided into training and test sets Mime-Type: application/zip File size: 629kB