CoChat
Sign Up
Cited by 75Sentiment Analysis and Opinion MiningComputational and Text Analysis MethodsHate Speech and Cyberbullying Detection

From classification to quantification in tweet sentiment analysis

Open access
Gao, Wei, Sebastiani, Fabrizio·2016·Social Network Analysis and Mining
DOI 10.1007/s13278-016-0327-z
Open this paper in CoChat — free account

Integrity signals

Registry

Crossref · 10.1007/s13278-016-0327-z

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Automatic classification can introduce biases in the data, particularly when the end goal is measuring prevalence in the data rather than estimating specific labels.

    “automatic classification, a common operation of this kind, can introduce biases in the data. This is particularly problematic when the end goal is not the estimation of specific labels, but measuring their prevalence in the data [e.g., Gao and Sebastiani (2016) discuss why the distinction between the two tasks is important, and why different evaluation metrics should apply].”

    From Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019) · cites this paper as Gao and Sebastiani, 2016

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Gao, W., & Sebastiani, F.
Affiliations
Hamad bin Khalifa University (QA)
Corresponding author
Sebastiani, Fabrizio
ORCID
Venue
Social Network Analysis and Mining
Publisher
Springer Science and Business Media LLC
Published
2016-04-12
Volume
6
Issue
1
ISSN
  • 1869-5450 (ISSN-L)
  • 1869-5469
DOI
10.1007/s13278-016-0327-z
OpenAlex
W2342355650
Cited by
75
References
3
Citations by year
2026: 2 · 2025: 5 · 2024: 5 · 2023: 13 · 2022: 10 · 2021: 9 · 2020: 10 · 2019: 8 · 2018: 6 · 2017: 6 · 2016: 1
FWCI
5.77
Type
journal article
Language
en
Open access
Licence
Locations
  • Social Network Analysis and Mining (publishedVersion)
  • Singapore Management University Institutional Knowledge (InK) (Singapore Management University) (submittedVersion, other-oa)
  • ISTI Open Portal (submittedVersion, other-oa)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
  • Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
Keywords
Twitter sentiment analysis, Twitter, evaluation metrics, learning algorithms, social media sentiment analysis

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review