Feature-Based Twitter Sentiment Analysis With Improved Negation Handling
Bibliographic record
Abstract
There is remarkable progress in the research of Twitter sentiment analysis (TSA) which is a technique of extracting opinion by automatically processing digital data. In this article, we propose a feature-based TSA system in conjunction with improved negation accounting by leveraging different types of features such as lexicon-based, morphological, POS-based, n-gram features, and many more, which would be used for classifier training and have the strong impact on polarity determination. We use three different state-of-the-art classifiers such as support vector machine (SVM), Naive Bayesian, and decision tree, and the series of experiments are conducted to determine which classifier works well with which feature group. In addition, this work focuses on investigating a significant linguistic phenomenon called negation which can either change polarity or strength of polarity of opinionated words. To enhance the classification performance, an algorithm is also developed to handle those negation tweets in which the presence of negation does not necessarily mean negation. The proposed feature-based Twitter system with negation accounting is evaluated on the benchmark Twitter data set SemEval-2013 Task 2. The experimental results demonstrate that the SVM classifier outperforms the other classifiers and the state-of-the-art TSA system developed by the NRC Canada winning team of SemEval-2013 Task 2. In addition, extensive experiments are also conducted to demonstrate that the proposed negation strategy with incorporated negation exception rules provides a substantial improvement by preventing misclassification of tweets. Finally, impact of each preprocessing module on classification performance is presented.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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 source (direct Gemma or distilled Codex), 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".