Bibliographic record
Abstract
A Review of: Wang, Y. (2022). Using machine learning and natural language processing to analyze library chat reference transcripts. Information Technology and Libraries, 41(3). https://doi.org/10.6017/ital.v41i3.14967 Objective – The study sought to develop a model to predict if library chat questions are reference or non-reference. Design – Supervised machine learning and natural language processing. Setting – College of New Jersey academic library. Subjects – 8,000 Springshare LibChat transactions collected from 2014 to 2021. Methods – The chat logs were downloaded into Excel, cleaned, and individual questions were labelled reference or non-reference by hand. Labelled data were preprocessed to remove nonmeaningful and stop words, and reformatted to lowercase. Data were then stemmed to group words with similar meaning. The feature of question length was then added and data were transformed from text to numeric for text vectorization. Data were then divided into training and testing sets. The Python packages Natural Language Toolkit (NLTK) and scikit-learn were used for analysis, building random forest and gradient boosting models which were evaluated via confusion matrix. Main Results – Both models performed very well in precision, recall and accuracy, with the random forest model having better overall results than the gradient boosting model, as well as a more efficient fit time, though slightly longer prediction time. Conclusion – High volume library chat services could benefit from utilizing machine learning to develop models that inform plugins or chat enhancements to filter chat queries quickly.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.003 | 0.570 |
| Open science | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
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".