Bibliographic record
Abstract
In this paper, the main features of parametrical words within a sentiment lexicon are determined.The data for the research are client reviews in the Russian language taken from the bank client rating; the domain under study is bank service quality.The sentiment lexicon structure is presented; it includes two primary classes (positive and negative words) and three secondary classes (increments, polarity modifiers, and polarity antimodifiers).This lexicon is used as the main tool for the sentiment analysis carried out by two methods: the Nave Bayes classifier and the REGEX algorithm.Parametrical words are referred to as the words denoting the value of some domain-specific parameter, e.g. the client's time consuming.To distinguish the main features of parametrical words, the parameters relevant for the bank service quality domain are determined.The revised lexicon structure is proposed, with a new class (decrements) added.The results of the research demonstrate that parametrical words express implicit opinions, since parameters are not usually named directly in reviews.Only a small number of parametrical words can be ranged into the primary classes (positive or negative), but this ranging is domain-specific.It is the parameter that determines the domain specificity of such words.Most parametrical words are ranged into the secondary classes, and this ranging can be considered universal.The parametrical words denoting the increase of a parameter should be ranged into the increment class, as they intensify positive or negative emotions.The parametrical words denoting the decrease of a parameter should be ranged into the decrement class, as they reduce positive or negative emotions.The evident progress on the way to the sentiment lexicon universalization can be achieved by classifying parametrical words within the sentiment lexicon.
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 | 0.005 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| 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; 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".