MétaCan
Menu
Back to cohort
Record W3154106396 · doi:10.1109/tcss.2021.3069413

Feature-Based Twitter Sentiment Analysis With Improved Negation Handling

2021· article· en· W3154106396 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

aboutThe title or abstract carries a Canadian signal from the geographic lexicon.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueIEEE Transactions on Computational Social Systems · 2021
Typearticle
Languageen
FieldComputer Science
TopicSentiment Analysis and Opinion Mining
Canadian institutionsnot available
Fundersnot available
KeywordsNegationComputer scienceArtificial intelligenceSemEvalSentiment analysisClassifier (UML)Support vector machinePreprocessorNatural language processingLexiconSalience (neuroscience)Machine learningFeature (linguistics)Naive Bayes classifierPattern recognition (psychology)Task (project management)

Abstract

fetched live from OpenAlex

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.

Full frame distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.970
Threshold uncertainty score0.683

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.019
GPT teacher head0.259
Teacher spread0.240 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it