MétaCan
Menu
Back to cohort
Record W4290928156 · doi:10.1016/j.procs.2022.07.023

Live Sentiment Analysis Using Multiple Machine Learning and Text Processing Algorithms

2022· article· en· W4290928156 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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueProcedia Computer Science · 2022
Typearticle
Languageen
FieldComputer Science
TopicSentiment Analysis and Opinion Mining
Canadian institutionsTrent UniversityThompson Rivers University
Fundersnot available
KeywordsComputer scienceSentiment analysisNaive Bayes classifierLexiconMachine learningArtificial intelligenceSupport vector machineAlgorithmData stream miningData mining

Abstract

fetched live from OpenAlex

Due to the massive amount of data being generated on the platform, Twitter has been the subject of numerous sentiment analysis studies. Such social network services generate massive unstructured data streams which make working with them very challenging. The aim of this study is to reliably analyze the sentiment of trending tweets in the Twitter API data stream using a combination of different algorithms to achieve a consensus. The methods we implemented include Support-Vector Machine, Naive Bayes, Textblob, and Lexicon Approach. The hypothesis is that using these methods together would enable us to get more accurate results. Using a labeled dataset to test our model, the results show that the combination of these four algorithms all together performed best with an overall accuracy of 68.29%. We conclude that our combination method of analysis is suitable and fast enough for our data stream and also accurate for analyzing sentiment.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScience and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.829
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.005
Science and technology studies0.0020.000
Scholarly communication0.0010.001
Open science0.0010.003
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 head0.020
GPT teacher head0.270
Teacher spread0.250 · 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