CoChat
Sign Up
Cited by 160Financial Markets and Investment StrategiesStock Market Forecasting MethodsComputational and Text Analysis Methods

News or Noise? Using Twitter to Identify and Understand Company-specific News Flow

Sprenger, Timm O., Sandner, Philipp G., Tumasjan, Andranik, Welpe, Isabell M.·2014·Journal of Business Finance & Accounting
DOI 10.1111/jbfa.12086
Open this paper in CoChat — free account

Abstract

Abstract This study presents a methodology for identifying a broad range of real‐world news events based on microblogging messages. Applying computational linguistics to a unique dataset of more than 400,000 S&P 500 stock‐related Twitter messages, we distinguish between good and bad news and demonstrate that the returns prior to good news events are more pronounced than for bad news events. We show that the stock market impact of news events differs substantially across different categories.

Integrity signals

Registry

Crossref · 10.1111/jbfa.12086

Cites

68 of 68 references verified0 citation errors · 0 not checkable

Statistics

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

Claims the paper makes

This paper’s full text isn’t openly available, 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?

  • Sprenger et al.'s Naive Bayes sentiment classifier, trained on 2,500 examples, yields a 10-fold cross-validation accuracy of 64.2%.

    “In a closely related work by Sprenger et al. [36], they use Naive Bayes for sentiment classification. Their classifier is trained on 2,500 examples, and the 10-fold cross-validation yields Accuracy of 64.2%.”

    From The Effects of Twitter Sentiment on Stock Price Returns (2015) · cites this paper as [36]

  • Sprenger et al. detect 224 out of 672 earnings announcement events, yielding a recall of 33%.

    “In contrast, Sprenger et al. [36] detect 224 out of 672 EA events, yielding the recall of 33%.”

    From The Effects of Twitter Sentiment on Stock Price Returns (2015) · cites this paper as [36]

  • These results are similar to the ones reported by Sprenger et al.

    “These results are similar to the ones reported by Sprenger at al. [36].”

    From The Effects of Twitter Sentiment on Stock Price Returns (2015) · cites this paper as [36]

  • Sprenger et al. show a statistically significant increase in cumulative abnormal return values even before positive event days.

    “In addition, the authors show statistically significant increase in the CAR values even before the positive event days.”

    From The Effects of Twitter Sentiment on Stock Price Returns (2015) · cites this paper as [36]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Sprenger, T. O., Sandner, P. G., Tumasjan, A., & Welpe, I. M.
Affiliations
Technical University of Munich (DE)
Corresponding author
  • Sandner, Philipp G.
  • Welpe, Isabell M.
ORCID
Venue
Journal of Business Finance & Accounting
Publisher
Wiley
Published
2014-09
Volume
41
Issue
7-8
Pages
791-830
ISSN
  • 0306-686X (ISSN-L)
  • 1468-5957
DOI
10.1111/jbfa.12086
OpenAlex
W1923555227
Cited by
160
References
65
Citations by year
2026: 8 · 2025: 12 · 2024: 14 · 2023: 16 · 2022: 17 · 2021: 18 · 2020: 13 · 2019: 14 · 2018: 16 · 2017: 14 · 2016: 11 · 2015: 7
FWCI
19.50
Type
journal article
Language
en
Open access
closed
Licence
onlinelibrary.wiley.com/termsAndConditions#vor (vor, 41 d)
Locations
  • Journal of Business Finance & Accounting (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
Topics
  • Social Sciences › Economics, Econometrics and Finance › Finance › Financial Markets and Investment Strategies
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
Keywords
Twitter, microblogging, news event detection, sentiment analysis, stock returns, S&P 500 stocks, social media and stock markets

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