Sentiment analysis as a measure of conservation culture in scientific literature
Bibliographic record
Abstract
Culturomics is emerging as an important field within science, as a way to measure attitudes and beliefs and their dynamics across time and space via quantitative analysis of digitized data from literature, news, film, social media, and more. Sentiment analysis is a culturomics tool that, within the last decade, has provided a means to quantify the polarity of attitudes expressed within various media. Conservation science is a crisis discipline; therefore, accurate and effective communication are paramount. We investigated how conservation scientists communicate their findings through scientific journal articles. We analyzed 15,001 abstracts from articles published from 1998 to 2017 in 6 conservation-focused journals selected based on indexing in scientific databases. Articles were categorized by year, focal taxa, and the conservation status of the focal species. We calculated mean sentiment score for each abstract (mean adjusted z score) based on 4 lexicons (Jockers-Rinker, National Research Council, Bing, and AFINN). We found a significant positive annual trend in the sentiment scores of articles. We also observed a significant trend toward increasing negativity along the spectrum of conservation status categories (i.e., from least concern to extinct). There were some clear differences in the sentiments with which research on different taxa was reported, however. For example, abstracts mentioning lobe finned fishes tended to have high sentiment scores, which could be related to the rediscovery of the coelacanth driving a positive narrative. Contrastingly, abstracts mentioning elasmobranchs had low scores, possibly reflecting the negative sentiment score associated with the word shark. Sentiment analysis has applications in science, especially as it pertains to conservation psychology, and we suggest a new science-based lexicon be developed specifically for the field of conservation.
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 | 0.015 | 0.047 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.021 | 0.015 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.000 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".