Augmented PHEME — Boston Bombings Rumour Dataset
A Twitter dataset of 4,952 tweets (1,238 rumour, 3,714 non-rumour) from the 2013 Boston Marathon bombings, collected by Zubiaga, Liakata, and Procter — Augmented PHEME (Zenodo, 2019). Each record contains tweet text, binary rumour/non-rumour label, timestamp, reaction thread structure linking source tweets to replies. Augmented extension of PHEME covering the Boston Marathon bombings event with both rumour threads and non-rumour threads, providing a balanced benchmark for rumour detection with reaction graph structure. Suitable for rumour detection, misinformation classification, crisis communication analysis, stance detection, conversational thread modelling.
Cite this dataset at
augmented-pheme-bostonbombings.echo.directory
Analytics
The full graph has 1,872 nodes; this view shows the 1,000-node sample the pipeline drew for display. Node size is centrality, colour is community.
Topic 0
Topic 1
Topic 2
Topic 3
Topic 4
Topic 5
Topic 6
Topic 7
Topic 8
Topic 9
Topic 10
Topic 11
Show all 28 topics
Topic 12
Topic 13
Topic 14
Topic 15
Topic 16
Topic 17
Topic 18
Topic 19
Topic 20
Topic 21
Topic 22
Topic 23
Topic 24
Topic 25
Topic 26
Topic 27
Computed over the full corpus.
Record
- Catalog key
augmented-pheme-bostonbombings- Authors
- Han, Sooji; Gao, Jie; Ciravegna, Fabio
- Year
- 2019
- Source paper
- Neural language model based training data augmentation for weakly supervised early rumor detection
- DOI / arXiv
- 10.1145/3341161.3342892
- License
- Creative Commons Attribution 4.0 (CC-BY-4.0)
- Records
- 4,952
- Nodes
- 1,872
- Edges
- 1,482 (directed)
- Nodes are
- tweet
- Edges are
- reply
- Attributes
- nodes have attributes; edges have attributes
- Languages
- en
- Collected
- 2013-04 (2010s)
- Tasks
- Rumour & veracity classification (binary;
is_rumour) inferred
From the graph: link prediction, community detection - Region
- Global (inferred: the platform is used worldwide)
Provenance
- Originally published at
- https://zenodo.org/records/3249977 link checked
- Hosted copy
- Mirrored on echo.directory on 2026-10-09, 5.1 MB across 1883 files. Checksums in MANIFEST.json.
Citations
Neural Language Model Based Training Data Augmentation for Weakly Supervised Early Rumor Detection
Sooji Han, Jie Gao, F. Ciravegna
Journal Article · International Conference on Advances in Social Networks Analysis and Mining · 2019
Cited by
- Identifying Possible Rumor Spreaders on Twitter: A Weak Supervised Learning Approach
Shakshi Sharma, Rajesh Sharma · IEEE International Joint Conference on Neural Network · 2020 · cited 37× - A survey on pragmatic processing techniques
Rui Mao, Mengshi Ge et al. · Information Fusion · 2024 · cited 31× - Hybrid weakly supervised learning with deep learning technique for detection of fake news from cyber propaganda
Liyakathunisa Syed, A. Alsaeedi et al. · Array · 2023 · cited 27× - RP-DNN: A Tweet Level Propagation Context Based Deep Neural Networks for Early Rumor Detection in Social Media
Jie Gao, Sooji Han et al. · International Conference on Language Resources and Evaluation · 2020 · cited 27× - A model for early rumor detection base on topic-derived domain compensation and multi-user association
Zhou Yang, Yu-Cai Pang et al. · Expert systems with applications · 2024 · cited 25×
Show all 10
- Enhancing rumor detection with data augmentation and generative pre-trained transformer
Mojgan Askarizade · Expert systems with applications · 2024 · cited 15× - Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models
P. Przybyla, Euan McGill et al. · Conference on Empirical Methods in Natural Language Processing · 2024 · cited 14× - Verifying the robustness of automatic credibility assessment
Piotr Przybyła, A. Shvets et al. · Natural Language Processing · 2023 · cited 14× - A novel domain and event adaptive tweet augmentation approach for enhancing the classification of crisis related tweets
Dharini Ramachandran, P. Ramasubramanian · Data & Knowledge Engineering · 2021 · cited 13× - Topic to Image: A Rumor Detection Method Inspired by Image Forgery Recognition Technology
Yucai Pang, Xuehong Li et al. · IEEE Transactions on Computational Social Systems · 2024 · cited 11×
Citation data from Semantic Scholar, retrieved 2026-10-22.
How to cite
BibTeX
@misc{echo2026,
title = {ECHO: Exploratory Compendium of Humanity Online},
author = {Switzer, Braden and Zafarani, Reza},
year = {2026},
url = {https://echo.directory},
note = {Syracuse University}
}
@inproceedings{Han_2019,
series = {ASONAM ’19},
title = {Neural language model based training data augmentation for weakly supervised early rumor detection},
url = {http://dx.doi.org/10.1145/3341161.3342892},
doi = {10.1145/3341161.3342892},
booktitle = {Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining},
publisher = {ACM},
author = {Han, Sooji and Gao, Jie and Ciravegna, Fabio},
year = {2019},
month = Aug,
pages = {105–112},
collection = {ASONAM ’19}
} APA
Switzer, B., & Zafarani, R. (2026). ECHO: Exploratory Compendium of Humanity Online [Data repository]. Syracuse University. https://echo.directory
Han, S., Gao, J., & Ciravegna, F. (2019). Augmented PHEME — Boston Bombings Rumour Dataset [Data set]. https://doi.org/10.1145/3341161.3342892
MLA
Switzer, Braden, and Reza Zafarani. ECHO: Exploratory Compendium of Humanity Online. Syracuse University, 2026, echo.directory.
Han, Sooji, et al. Augmented PHEME — Boston Bombings Rumour Dataset. 2019, doi.org/10.1145/3341161.3342892.