Predicting the environment from social media: A collective classification approach
- Submitting institution
-
University of the West of England, Bristol
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 6004500
- Type
- D - Journal article
- DOI
-
10.1016/j.compenvurbsys.2020.101487
- Title of journal
- Computers, Environment and Urban Systems
- Article number
- 101487
- First page
- -
- Volume
- 82
- Issue
- -
- ISSN
- 0198-9715
- Open access status
- Compliant
- Month of publication
- April
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper describes the proposed collective prediction framework. It is the first known work that investigates the usefulness of Flickr tags to make predictions and defines the neighbourhood structure of a given environmental feature. The method is evaluated on a range of different tasks, covering subjective assessments (in particular scenicness) and measurable features (e.g. temperature or precipitation), and covering different spatial resolutions. It can be used in many applications as a spatial and/or environmental data interpolation method. Some parts of the paper were presented in the International Conference on Spatial Information Theory (COSIT 2017).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
