Social Media Data, Machine Learning and Causal Inference
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
Social Media data and machine learning techniques together pose an unprecedented opportunity to researchers in building theories. Machine learning using social media data can be considered a specific mixed method that combines qualitative methods and unstructured data with quantitative techniques. The extant approaches in social computing and machine learning in Information Systems literature, however, are criticized producing predictions without causal inferences as well as largely focused on social media as a context of interest and hence yet to be recognized in their utility in building generalizable theories. Through this study, we attempt to address these limitations by combining two text analysis techniques using social media data in the context of a natural experiment. First, we propose a novel framework that combines unsupervised (topic modeling) and supervised (sentiment analysis) machine learning abductively applied on longitudinal Twitter data. In turn, the approach facilitates decontextualizing the text from social media that can be used to theorize at a higher level of abstraction. Second, we exploit a natural experiment to integrate machine learning technique with causal inference. Together, by integrating topic modeling and sentiment analysis, and leveraging empirical setting of a natural experiment, this study demonstrates a novel framework to theory building using social media data.
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 | 0.005 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 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