Designing a Natural Language Processing System to Support Social Science Research
Bibliographic record
Abstract
The rapid development of machine learning has delivered new approaches, methods, and tools to multiple domains. I see potential for these developments, specifically natural language processing (NLP), to provide new insights, novel methods, and larger scale to social science research. However, novel NLP methods require substantial technical skills to implement. Some of the highest adoption of novel technical tools is in the area of social media analysis, where the volume of source material can overwhelm methods that rely on human capacity. My PhD dissertation aims to bridge the gap between NLP technologies and the unique needs of social science research by contributing to the development of an open-source NLP tool specifically tailored for social science researchers that reduces barriers to entry. The goal is to empower social science researchers by providing more opportunities to explore data in novel ways. This paper outlines the objectives, methodology, and expected outcomes of the proposed research study, which includes designing the development process, requirement analysis, prototyping an NLP tool, evaluating its usability and performance, and providing support for its integration into the research workflow.
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 | 0.023 | 0.048 |
| Meta-epidemiology (narrow) | 0.001 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.006 | 0.011 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.011 | 0.008 |
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".