MétaCan
Menu
Back to cohort
Record W2766367305 · doi:10.2495/dne-v13-n1-60-70

Classification of tweets with a mixed method based on pragmatic content and meta-information

2018· article· en· W2766367305 on OpenAlexvenueno aff
Miriam Esteve, Filomeno Davide Miro, A. Rabasa

Bibliographic record

VenueInternational Journal of Design & Nature and Ecodynamics · 2018
Typearticle
Languageen
FieldComputer Science
TopicHate Speech and Cyberbullying Detection
Canadian institutionsnot available
Fundersnot available
KeywordsContent (measure theory)Computer scienceInformation retrievalArtificial intelligenceNatural language processingMathematics

Abstract

fetched live from OpenAlex

The sharp rise in social networks in any field of opinion has led to the increasing importance of content analysis.Due to the concretion of the texts published on Twitter from its limitation to 140 characters, this network is the most suitable for the analysis and classification of opinions according to different criteria.Therefore, there are multiple tweet analysis tools oriented from the perspective of semantics for trying to classify content characteristics such as feeling and polarity.In this paper, the authors present a new approach to classification from a different perspective.The proposed approach addresses a complex mixed model from a perspective of pragmatics, the analysis of opinions in the context of their issuer carried out by a panel of experts, along with the classification of the type of discourse by considering the meta-information of the tweet.From this new approach, the paper presents a complete and complex analysis process of Big Data, which covers all the characteristic phases of the life cycle: capture, storage, preprocessing and analysis of a tweets database.The aim is to classify the tweets as violent or non-violent in their reference to terrorist acts.If the classification models based on the metadata of tweets reach acceptable levels of accuracy, this methodology will offer a reliable and semiautomatic alternative for tweet classification.

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)0.004
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: Methods · Consensus signal: Methods
Teacher disagreement score0.015
Threshold uncertainty score0.023

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.011
Meta-epidemiology (narrow)0.0020.000
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0150.006
Science and technology studies0.0010.001
Scholarly communication0.0030.003
Open science0.0010.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0040.003

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 head0.024
GPT teacher head0.270
Teacher spread0.246 · 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
GenreMethods

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

Citations5
Published2018
Admission routes1
Has abstractyes

Explore more

Same venueInternational Journal of Design & Nature and EcodynamicsSame topicHate Speech and Cyberbullying DetectionFrench-language works237,207