Sentiment Analysis on Climate Change using Twitter Data
Bibliographic record
Abstract
The objective is to illuminate the nuanced and complex public opinion surrounding climate change conversations on Twitter. The work employs advanced machine learning methods and natural language processing techniques, notably Support Vector Machines (SVM), to conduct a global-scale sentiment analysis using a sizable dataset that was obtained from a reliable third-party source. This study's main goal is to pinpoint the various ways that emotion is expressed in the context of climate change conversation; both positive and negative expressions are taken into account. The authenticity and utility of the selected third-party dataset—obtained through Kaggle and made possible by a Canadian Innovation Foundation JELF grant awarded to Chris Bausch at the University of Waterloo—are critically evaluated. The SVM-based sentiment analysis demonstrates how well the chosen methodology reflects the complexity of sentiment in climate change debates on Twitter, with an exceptional F1 score of 0.70. The implications of the research include communication strategies for legislators, organizations seeking to reach a global audience, and climate change advocates. By utilizing an external dataset and applying the Support Vector Machines algorithm's sentiment analysis, this study advances our comprehension of the intricate relationship between the public's perspective of climate change and social media conversation. To sum up, this study shows the value of SVM in detecting subtleties of sentiment in huge databases, contributing significant new knowledge to the developing subject at the nexus of environmental consciousness and social media dynamics.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".