International Journal of Market Research, Volume 66, Issue 5, Page 610-630, September 2024.
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 (R2). 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.
International Journal of Market Research, Volume 66, Issue 5, Page 610-630, September 2024. <br/>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 (R2). 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. Read More
Related posts:
How Virtual Reality Can Increase Effectiveness of Prosocial Advertising: Put Yourself in the Donees Shoes: The Effect of Virtual Reality on Charitable Donations
Increasing physical activity among Indonesian adolescents: a social marketing intervention reflection
Upselling through upgrading: The role of employee engagement
The double-edged sword of envy: effects of envy type and regulatory focus on consumer decision-making
Integrating emotion regulation, emotional intelligence, and emotion-focused coping in the entrepreneurial context: A review and research agenda
Privacy concerns and social desirability bias