Context-Specific Sentiment Lexicon Expansion via Minimal User Interaction
Bibliographic record
Abstract
One of the important factors in the performance of sentiment analysis methods is having a comprehensive sentiment lexicon. However, since sentiment words have different polarities not only in different domains, but also in different contexts within the same domain, constructing such context-specific sentiment lexicons is not an easy task. The high costs of manually constructing such lexicons motivate researchers to create automatic methods for finding sentiment words and assigning their polarities. However, existing methods may encounter ambiguous cases with contradictory evidence which are hard to automatically resolve. To address this problem, we aim to engage the user in the process of polarity assignment and improve the quality of the generated lexicon via minimal user effort. A novel visualization is employed to present the results of the automatic algorithm, i.e., the extracted sentiment pairs along with their polarities. User interactions are provided to facilitate the supervision process. The results of our user study demonstrate (1) involving the user in the polarity assignment process improves the quality of the generated lexicon significantly, and (2) participants in the study preferred our visual interface and conveyed that it is easier to use compared to a text-based interface.
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 | 0.000 |
| 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) | 0.001 | 0.001 |
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".