Natural Language Processing to Understand Human Activities Impacted by Hydroelectric Energy Projects
Bibliographic record
Abstract
Sustainability and large infrastructure projects are intricately linked. When considering large and disruptive infrastructure projects, proponents, regulators, and stakeholders consider a variety of information sources to understand how the project and its environmental changes will impact people living in the region. This is often done using small data, through interviews, town halls, and surveys. Big Data approaches have potential to augment these methods; for example, novel approaches natural language processing (NLP) on social media data can reveal human-nature interactions in impacted areas. Existing literature suggested that sentiment and frequency analyses can help us understand public attitudes. As a case study to illustrate this potential, we have examined public engagement with landscapes impacted by large hydroelectric development. We examined S6,122 geotagged image captions within 35 well-defined geographical locations associated with three dam projects in Canada: Mactaquac dam (New Brunswick), Oldman dam (Alberta), and Site C dam (British Columbia) on Instagram. The sentiment results of the study expressed a high positive attitude towards the three landscapes and frequency analysis exposed that the people are more likely to engage with the landscape in the context of fun, recreation, exercise activities and vacations. This can inform planning processes to ensure that impacts to these important interactions are examined and mitigated, achieving long-term environmental, social, and economic well-being.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".