Modelling sentiment and topics in letters written by 19th century immigrants in North America
Bibliographic record
Abstract
This thesis answers the call by the International Organization for Migration for researchers to listen to migrants.Based on the assumption that contemporary and historical migrants have similar experiences, this study takes as its subject 915 letters written by 218 immigrants in North America during the long 19th century.Within the framework of exploratory data analysis and using the tools of natural language processing and Bayesian linear regression, it measures sentiments, models topics and examines relationships between narrative features and temporal, structural and biographical variables.It also tests whether sentiment and topics predict cessation of correspondence, a potential indication that a migrant has successfully integrated into a new country.The hypothesis is that positivity in letters, signifying good experiences, correlates with an increased probability that correspondence will end.Sentiment was found to be mildly positive and topics mostly oriented around practical matters and relationship maintenance.These narrative features varied by time and writer traits, but they did not predict cessation of correspondence, which was mostly related to gender.Female migrants were more likely than men to continue writing.The findings are mostly in line with previous scholarship in the area of migrant correspondence, indicating that the methodology used here is valid.The quantitative techniques revealed subtle patterns, particularly around the influence of gender, and offered insight into how Bayesian multilevel modeling might address bias and representation in cultural datasets.Recommendations for future study include use of this technique for more nuanced modeling of migrant correspondence and for other work within the field of the digital humanities.Languages, Literatures and Cultures, who have offered their kindness and support to me in many different ways and for many years now.In particular, I am grateful to Prof
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 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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".