War brings about strong feelings of hate, and showcases the love of humanity. During war, social media is utilized for citizen journalism, supply organization and activism, but also for people to express their emotions. In this paper, we present a multi-modal multi-platform dataset that depicts the expression of love and hate towards both sides of the Israel-Hamas War. This dataset presents posts in English from Facebook and Instagram that contain the terms "love" or "hate" in the context of the war during 7 October 2023 (onset of war) to 31 December 2023. We find that over time, the number of posts on the war decreased, suggesting interest in the war has waned; posts about Love reference religion while posts about Hate references hostility; and emojis in Love posts represent hearts, peace and listening while emojis in Hate posts represent being watched, sadness and warning. Finally, we generated Instagram posts with GPT4-V using our dataset as a reference, and the model returned posts of generic love messages with art-form images. We hope our dataset is useful to researchers studying multi-modal and multi-platform information and emotions on social media during a war.
No takes yet. Share an insight, caveat, or question.
Ng et al. (2024) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: