A Twitter dataset of 60,082 tweets across 6 crisis events (0 on-topic, 60,082 off-topic), collected by Olteanu et al. via crowdsourcing for 6 crisis events. Each record contains tweet text, on-topic/off-topic label (crowdsourced majority voting), crisis type, country, year. The dataset is notable for its Systematically collected dataset of 6 crisis events with crowdsourced on-topic/off-topic labels from at least 3 workers per tweet, enabling comparative analysis of tweet relevance across different crises. Cumulative version combines all events into a single corpus.. Intended for research into crisis informatics, tweet filtering, on-topic detection, information extraction, crowdsourcing evaluation, event detection, situation awareness, multi-event NLP benchmarking.
A Twitter (crowdsourced hate speech annotation) dataset of 24,783 tweets labeled as hate speech (1,430), offensive (19,190), or neither (4,163), collected by Davidson et al. via CrowdFlower crowdsourcing (2017). Each record contains tweet text, majority class label (0=hate/1=offensive/2=neither), per-label coder counts, total coder count. Davidson et al. 2017 is one of the most cited hate speech datasets, with 24,783 tweets annotated by multiple crowdworkers — distinguished by separating hate speech from merely offensive language. Suitable for hate speech detection, offensive language classification, content moderation, NLP benchmarking, crowdsourced annotation research.
A Twitter dataset of 10,031 tweets (0 on-topic, 10,031 off-topic), collected by Olteanu et al. via crowdsourcing for the Alberta Floods 2013 crisis. Each record contains tweet text, on-topic/off-topic label (crowdsourced majority voting), crisis type, country, year. The dataset is notable for its tweets from the Alberta Floods 2013 crisis, labeled by crowdsourcing workers for on-topic/off-topic classification with majority voting from at least 3 workers per tweet. Intended for research into crisis informatics, tweet filtering, on-topic detection, information extraction, crowdsourcing evaluation, event detection, situation awareness.
A Twitter dataset of 10,012 tweets (0 on-topic, 10,012 off-topic), collected by Olteanu et al. via crowdsourcing for the Boston Bombings 2013 crisis. Each record contains tweet text, on-topic/off-topic label (crowdsourced majority voting), crisis type, country, year. The dataset is notable for its tweets from the Boston Bombings 2013 crisis, labeled by crowdsourcing workers for on-topic/off-topic classification with majority voting from at least 3 workers per tweet. Intended for research into crisis informatics, tweet filtering, on-topic detection, information extraction, crowdsourcing evaluation, event detection, situation awareness.
A Twitter dataset of 10,006 tweets (0 on-topic, 10,006 off-topic), collected by Olteanu et al. via crowdsourcing for the West Texas Explosion 2013 crisis. Each record contains tweet text, on-topic/off-topic label (crowdsourced majority voting), crisis type, country, year. The dataset is notable for its tweets from the West Texas Explosion 2013 crisis, labeled by crowdsourcing workers for on-topic/off-topic classification with majority voting from at least 3 workers per tweet. Intended for research into crisis informatics, tweet filtering, on-topic detection, information extraction, crowdsourcing evaluation, event detection, situation awareness.
A Twitter dataset of 9,992 tweets (0 on-topic, 9,992 off-topic), collected by Olteanu et al. via crowdsourcing for the Oklahoma Tornado Season 2013 crisis. Each record contains tweet text, on-topic/off-topic label (crowdsourced majority voting), crisis type, country, year. The dataset is notable for its tweets from the Oklahoma Tornado Season 2013 crisis, labeled by crowdsourcing workers for on-topic/off-topic classification with majority voting from at least 3 workers per tweet. Intended for research into crisis informatics, tweet filtering, on-topic detection, information extraction, crowdsourcing evaluation, event detection, situation awareness.
Twitter (X)