MétaCan
Menu
Back to cohort
Record W3080989070 · doi:10.1145/3410566.3410594

A practical application for sentiment analysis on social media textual data

2020· article· en· W3080989070 on OpenAlexaff
Colton Aarts, Fan Jiang, Liang Chen

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicSentiment Analysis and Opinion Mining
Canadian institutionsUniversity of Northern British Columbia
Fundersnot available
KeywordsSentiment analysisComputer scienceSocial mediaData scienceInformation retrievalFeelingProduct (mathematics)World Wide WebNatural language processingPsychology

Abstract

fetched live from OpenAlex

With the amount of data that is available today in textual form, it is essential to be able to extract as much useful information as possible from them. While some textual documents are easy to be understood, other textual documents may need extra processes to discover the hidden information within it. For instance, how the author was feeling while writing this piece of text, or what emotions authors are expressing in this piece of text. The idea of discovering what emotions are expressed in a textual document is known as sentiment analysis. The interest in sentiment analysis has been steadily growing in the past decade. Being able to accurately detect and measure the different emotions present in a text has become more and more useful as the availability of online resources has increased. These resources can range from product reviews to social media content. Each of these resources presents their own distinct challenges while still sharing the core techniques and procedures. In this paper, we introduce an application that can detect four distinct emotions from social media posts. We will first outline the techniques we have used as well as our outcomes, then discuss the challenges that we faced, and finally, our proposed solutions for the continuation of this project.

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 imitation

Not 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.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.011
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.014
Threshold uncertainty score0.047

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.011
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.003
Science and technology studies0.0010.000
Scholarly communication0.0020.002
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0140.010

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 head0.172
GPT teacher head0.387
Teacher spread0.215 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations2
Published2020
Admission routes1
Has abstractyes

Explore more

Same topicSentiment Analysis and Opinion MiningFrench-language works237,207