The DOI matches its Crossref record; 69 of the 69 references it cites were found in a registry or an index.
The power of specific emotion analysis in predicting donations: A comparative empirical study between sentiment and specific emotion analysis in social media
Open accessAbstract
This paper investigates the role of sentiment and specific emotion analysis in forecasting donation behaviour within the context of social networking services (SNSs). The study empirically examines the influence of sentiment and specific emotion analysis on donation behaviour for two non-profit organizations (NPOs): The Fred Hollows Foundation (The Foundation) in both Australia and New Zealand, and The University of Auckland (UOA) in New Zealand. We collected and analysed 298,569 tweets from 106,349 users mentioning these NPOs, along with 5,175,359 tweets mentioning the top 20 US brands from 1,623,113 users. We found that NPOs are often associated with brands that induce joy. Furthermore, sadness expressed by marketers and joy expressed by users positively affected donations to The Foundation, while user-expressed anger positively influenced donations to UOA within the same month. A two-month rolling average analysis highlighted the significant effect of lingering negative emotions on monthly donations over time. Specific emotion analysis outperforms sentiment analysis by demonstrating a higher effect size ( R 2 ). We advocate for the application of the transformer-transfer learning method for specific emotion analysis when scrutinizing large-scale social media data and devising fundraising strategies.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“A growing body of research suggests that the recent generation of large language model (LLMs) excel, and in many cases outpace humans, at writing persuasively and empathetically, at inferring user traits from text, and at mimicking human-like conversation believably and effectively—without possessing any true empathy or social understanding.”
From The benefits and dangers of anthropomorphic conversational agents (2025) · cites this paper as [55]
In the citing paper
“In addition to persuasive writing, LLMs are now capable of reliably inferring emotion and sentiment from human-written text. In one study, a fine-tuned LLM was able to detect emotions in social media posts with 84% accuracy (55). Another study found precision levels of over 95% for LLMs assessing sentiment across multiple languages, with the ability to identify nuanced feelings such as nostalgia”
From The benefits and dangers of anthropomorphic conversational agents (2025) · cites this paper as [55]
In the citing paper
“For example, while LLMs’ persuasive writing has been associated with deception (25, 52) and harmful outcomes (27), recent studies have shown that it can equally be used to dissuade users of their beliefs in conspiracy theories (153), or drive users’ willingness to make donations for positive outcomes (55).”
From The benefits and dangers of anthropomorphic conversational agents (2025) · cites this paper as [55]
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 3×
“The RoBERTa model is an improvement over BERT because the former is based on a larger training data set, approximately 160 GB of text data (Liu et al., 2019), which is signi fi cantly more than BERT ’ s 13 GB (Devlin et al., 2018).”
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515 · cited 3×
“The RoBERTa model is an improvement over BERT because the former is based on a larger training data set, approximately 160 GB of text data (Liu et al., 2019), which is signi fi cantly more than BERT ’ s 13 GB (Devlin et al., 2018).”
Russell, J. A. (1980) · Journal of Personality and Social Psychology · doi:10.1037/h0077714 · Cited by 16,334 · cited 1×
“Other notable emotion models include Plutchik ’ s Wheel of Emotions (Plutchik & Kellerman, 1980), which identi fi es eight primary emotions and their varying intensities, and Russell ’ s circumplex model (Russell, 1980), which arranges emotions along the dimensions of arousal and valence.”
Baumeister, R. F., Bratslavsky, E., Finkenauer, C., & Vohs, K. D. (2001) · Review of General Psychology · doi:10.1037/1089-2680.5.4.323 · Cited by 7,678
VADER: a parsimonious rule-based model for sentiment analysis of social media text
Hutto, C., & Gilbert, E. (2014) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v8i1.14550 · Cited by 6,087 · cited 4×
“Next, we detail the methodology, which includes data collection, the application of sentiment analysis using the VADER method (Hutto & Gilbert, 2014) and speci fi c emotion analysis employing the transformer-transfer learning (TTL) method (Lee et al., 2023).”
InfluentialNegativity Bias, Negativity Dominance, and Contagion
Rozin, P., & Royzman, E. B. (2001) · Personality and Social Psychology Review · doi:10.1207/s15327957pspr0504_2 · Cited by 4,342 · cited 3×
“This discovery is consistent with the negativity bias theory, suggesting that negative emotions or experiences often have a more potent and enduring effect on individuals ’ decisions and behaviours than positive ones (Baumeister et al., 2001; Rozin & Royzman, 2001).”
Use of mass media campaigns to change health behaviour
Wakefield, M. A., Loken, B., & Hornik, R. C. (2010) · The Lancet · doi:10.1016/s0140-6736(10)60809-4 · Cited by 2,485 · cited 1×
“Wake fi eld et al. (2010) demonstrated that mass media campaigns via TV, radio, and newspapers can reduce harmful behaviours in areas such as tobacco use, alcohol consumption, drug use, heart disease prevention, and road safety.”
Nebraska Symposium on Motivation, 1969.
Schwartz, S., Arnold, W. J., & Levine, D. (1971) · American Sociological Review · doi:10.2307/2093748 · Cited by 2,171
Case Western Reserve University
Michaud, L. (1990) · doi:10.1093/gmo/9781561592630.article.a2284030 · Cited by 2,103 · cited 3×
“This discovery is consistent with the negativity bias theory, suggesting that negative emotions or experiences often have a more potent and enduring effect on individuals ’ decisions and behaviours than positive ones (Baumeister et al., 2001; Rozin & Royzman, 2001).”
Research works printed but not linked: 3
- 10.2139/ssrn.2648844 · DOI
- Koolen M., 2022, Journal of Computational Literary Studies, 1
- Statista, 2023, Top U.S. brands 2022
Cited by
The benefits and dangers of anthropomorphic conversational agents
Peter, S., Riemer, K., & West, J. D. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2415898122 · Cited by 110
Niimi, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.13069 · Cited by 19
“For a similar analysis, a previous study [22] which examined the relationship between the emotion of the posts on the social network and the total amount of monthly donation to the university constructed linear regression models based on predicted sentiments.”
MethodAugmenting military decision making with artificial intelligence
Vold, K. (2025) · Cambridge Forum on AI Law and Governance · doi:10.1017/cfl.2025.10022 · Cited by 4
“…the language we use when speaking with others, when writing or when engaging with a text-based AI system also indicates our emotional states (Lee, Paas & Ahn, 2024), and this analysis could likewise inform us about our current states, thereby increasing self-awareness about when we are most…”
Lee, S. J., Paas, L. J., Yuk, H., de Villiers, R., & Tipgomut, P. (2026) · Australasian Marketing Journal (AMJ) · doi:10.1177/14413582261442613
Self-citationYang, S. (2026) · IEEE International Conference on Power, Electronics and Green Energy (ICPEGE) · doi:10.1109/icpege67691.2026.11451449
“…user behavior prediction research mostly uses time series models such as LSTM to focus on short-term behaviors (such as the next-day interaction)[8], but ignores the driving role of emotions in behavior decisions; while the existing framework of user survival space only focuses on the "social -…”
Metadata
- Authors
- Lee, S. J., Paas, L., & Ahn, H. S.
- Affiliations
- University of Auckland (NZ)
- University of Auckland, New Zealand
- Corresponding author
- Lee, Sanghyub John
- Venue
- International Journal of Market Research
- Publisher
- SAGE Publications
- Published
- 2024-06-13
- Volume
- 66
- Issue
- 5
- Pages
- 610-630
- ISSN
- 1470-7853 (ISSN-L)
- 2515-2173
- OpenAlex
- W4399621484
- Cited by
- 6
- References
- 67
- Citations by year
- 2026: 3 · 2025: 3
- FWCI
- 0.89
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- International Journal of Market Research (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Social Sciences › Sociology and Political Science › Nonprofit Sector and Volunteering
- Social Sciences › Business, Management and Accounting › Marketing › Digital Marketing and Social Media
- Keywords
- sentiment analysis, donation behavior, nonprofit organizations, social media, Twitter, fundraising, joy, sadness, anger, brand associations, University of Auckland
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The power of specific emotion analysis in predicting donations: A comparative empirical study between sentiment and specific emotion analysis in social media. https://app.cochat.ai/papers/10.1177/14707853241261248
- The paper
- Lee, S. J., Paas, L., & Ahn, H. S. (2024). The power of specific emotion analysis in predicting donations: A comparative empirical study between sentiment and specific emotion analysis in social media. International Journal of Market Research. https://doi.org/10.1177/14707853241261248
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.