Customer Support on Twitter
A corpus of 2,811,774 tweets of customer support conversations on Twitter, collected by Stuart Axelbrooke (Thought Vector) with PointScrape and published on Kaggle: requests from consumers to 108 brand support accounts and the brands' replies, 1,537,843 inbound (consumer) tweets and 1,273,931 replies from the companies. Each tweet has an anonymised tweet ID, an anonymised author (the screen name of the account for the brand accounts, a number for the consumers), the posting time, the text, the ID of the tweet it answers and the IDs of the tweets that answer it. 99% of the tweets were posted between 1 October and 3 December 2017, with a few hundred earlier ones going back to 2008.
Cite this dataset at
customer-support-twitter.echo.directory
Analytics
The full graph has 702,777 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
- 1AmazonHelp
- 2AppleSupport
- 3Uber_Support
- 4SpotifyCares
- 5Delta
- 6Tesco
- 7AmericanAir
- 8TMobileHelp
- 9comcastcares
- 10British_Airways
- 11SouthwestAir
- 12VirginTrains
- 13Ask_Spectrum
- 14XboxSupport
- 15sprintcare
- 16hulu_support
- 17sainsburys
- 18GWRHelp
- 19AskPlayStation
- 20ChipotleTweets
- 1Postmates_Help
- 2TMobileHelp
- 3AzureSupport
- 4VirginTrains
- 5VerizonSupport
- 6AlaskaAir
- 7JetBlue
- 8VirginAmerica
- 9LondonMidland
- 10nationalrailenq
- 11AskTigogh
- 12CenturyLinkHelp
- 13AskLyft
- 14SW_Help
- 15SouthwestAir
- 16USCellularCares
- 17GWRHelp
- 18mediatemplehelp
- 19askpanera
- 20TwitterSupport
Computed over the full corpus.
Record
- Catalog key
customer-support-twitter- Authors
- Axelbrooke, Stuart
- Year
- 2017
- License
- CC BY-NC-SA 4.0 (CC-BY-NC-SA-4.0)
- Records
- 2,811,774
- Nodes
- 702,777
- Edges
- 1,107,572 (directed)
- Nodes are
- account (customer or brand support)
- Edges are
- reply
- Attributes
- nodes have attributes; edges have attributes
- Text corpus
- tweet text
- Languages
- en
- Collected
- 2017-09-26 to 2017-12-03 (2010s)
- Tasks
- From the graph: link prediction, community detection
- Region
- Global (inferred: the platform is used worldwide)
Provenance
- Originally published at
- https://www.kaggle.com/datasets/thoughtvector/customer-support-on-twitter link checked
- Original files as received
- The source files, unconverted, kept for reference: mirrored on echo.directory on 2026-10-20, 492.6 MB across 1 files. Checksums in MANIFEST.json. For use, start with the data package below.
- Data package
- Version 1.0.0 of this dataset as an ECHO Data Package: posts (2,811,774 rows).
- Structure
- Temporal (timestamped), Text, Threaded conversations
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}
}
@misc{axelbrooke2017customer,
title = {Customer Support on Twitter},
author = {Axelbrooke, Stuart},
publisher = {Kaggle (Thought Vector)},
year = {2017},
howpublished = {\url{https://www.kaggle.com/datasets/thoughtvector/customer-support-on-twitter}}
} APA
Switzer, B., & Zafarani, R. (2026). ECHO: Exploratory Compendium of Humanity Online [Data repository]. Syracuse University. https://echo.directory
Axelbrooke, S. (2017). Customer Support on Twitter [Data set]. https://customer-support-twitter.echo.directory/
MLA
Switzer, Braden, and Reza Zafarani. ECHO: Exploratory Compendium of Humanity Online. Syracuse University, 2026, echo.directory.
Axelbrooke, Stuart. Customer Support on Twitter. 2017, customer-support-twitter.echo.directory/.