Twitter conversations on sustainable development goals in Brazilian public universities using natural language processing
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract This study aims to provide insight into the behavior of Twitter conversations related to the Sustainable Development Goals (SDGs) by Brazilian public universities (UPBs) using Natural Language Processing (NLP). To achieve this goal, it was decided to develop descriptive research as it explores the characteristics of conversations focused on Twitter, one of the world's most used social media channels. Natural language processing (NLP) techniques based on the R programming language were used to extract and treat conversations held by the UPBs about the SDG objectives on Twitter. The study period is comprised of the creation of the first Twitter account by the universities until the data collection date, that is, between 2008 and 2022, therefore, 15 years of study, during this period, 326,114 tweets were identified. Evidence points to a substantial evolution in tweet publications by universities over the 15 years of studies. Thus, the practically zero publications in 2008 jumped to more than 15 thousand tweets in 2020. These findings show and confirm that universities use this social media to interact with their stakeholders. In addition, the results indicate that the analyzed universities make few publications on their Twitter about SDGs. In fact, of the 46 universities, only 6 tweeted about the subject, representing 13%. During the 15 years of studies, only 31 tweets were made on the subject. We found that the conversations and positions of universities on this subject in their social networks are few, insufficient, timid, and weak. As a second practical implication of this study, universities as centers of research, knowledge construction, and humanistic training urgently need to position themselves more on this subject in their social networks in order to demonstrate the relevance of the subject and inform about their accomplishments, and the need to everyone got involved in the theme.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it