An Open-Source Strategy for Documenting Events: The Case Study of the 42nd Canadian Federal Election on Twitter
Bibliographic record
Abstract
This article examines the tools, approaches, collaboration, and findings of the Web Archives for Historical Research Group around the capture and analysis of about 4 million tweets during the 2015 Canadian Federal Election. We hope that national libraries and other heritage institutions will find our model useful as they consider how to capture, preserve, and analyze ongoing events using Twitter. While Twitter is not a representative sample of broader society - Pew research shows in their study of US users that it skews young, college-educated, and affluent (above $50,000 household income) – Twitter still represents an exponential increase in the amount of information generated, retained, and preserved from 'everyday' people. Therefore, when historians study the 2015 federal election, Twitter will be a prime source.On August 3, 2015, the team initiated both a Search API and Stream API collection with twarc, a tool developed by Ed Summers, using the hashtag #elxn42. The hashtag referred to the election being Canada's 42nd general federal election (hence 'election 42' or elxn42). Data collection ceased on November 5, 2015, the day after Justin Trudeau was sworn in as the 42nd Prime Minister of Canada. We collected for a total of 102 days, 13 hours and 50 minutes. To analyze the data set, we took advantage of a number of command line tools, utilities that are available within twarc, twarc-report, and jq. In accordance with the Twitter Developer Agreement & Policy, and after ethical deliberations discussed below, we made the tweet IDs and other derivative data available in a data repository. This allows other people to use our dataset, cite our dataset, and enhance their own research projects by drawing on #elxn42 tweets. Our analytics included: breaking tweet text down by day to track change over time; client analysis, allowing us to see how the scale of mobile devices affected medium interactions; URL analysis, comparing both to Archive-It collections and the Wayback Availability API to add to our understanding of crawl completeness; and image analysis, using an archive of extracted images. Our article introduces our collecting work, ethical considerations, the analysis we have done, and provides a framework for other collecting institutions to do similar work with our off-the-shelf open-source tools. We conclude by ruminating about connecting Twitter archiving with a broader web archiving strategy.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.025 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.006 | 0.009 |
| Science and technology studies | 0.013 | 0.003 |
| Scholarly communication | 0.006 | 0.006 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".