MétaCan
Menu
Back to cohort
Record W2994294451

Content analysis of big qualitative data

2019· article· en· W2994294451 on OpenAlexaff
Антон Олейник

Bibliographic record

VenueInternational journal of open information technologies · 2019
Typearticle
Languageen
FieldSocial Sciences
TopicComputational and Text Analysis Methods
Canadian institutionsMemorial University of Newfoundland
Fundersnot available
KeywordsComputer scienceContent analysisData scienceCoding (social sciences)Information retrievalBig dataArtificial intelligenceData miningSociologySocial science
DOInot available

Abstract

fetched live from OpenAlex

When working with big data in science (research databanks, literature reviews) and everyday life (news aggregators), there is a need for mining, classifying and storing information. Information is defined as data in a processed form. The methodology of content analysis in its various forms, qualitative (manual coding), quantitative (words frequencies and co-occurrences) and mixed methods (creation of ad hoc dictionaries based on substitution), offers a tool to address this issue. Interest in content analysis emerged as early as in the 1970s, yet it remains relatively unknown outside of sociology, linguistics and communication studies. Content analysis allows converting qualitative data (texts, images) into digital format (vectors and matrices) and subsequent manipulating digital information using linear algebra, multidimensional scaling and other tools from natural sciences. The conversion into digital formal also paves the way to machine learning. Supervised machine learning looks particularly promising since it implies keeping focus on interpretation of data proper to interpretative sociology. Supervised machine learning is compatible with mixed methods content analysis. The existing program for computer-assisted content analysis (QDA Miner, Atlas TI, NVivo etc.) have several limitations. Restrictions on the number of their users (coders) refer to one of the limitations. The creation of on-line platforms for content analysis allows bypassing this and some other limitations. The idea of creating an on-line databank for qualitative data and a platform for content analyzing it is discussed. In contrast to quantitative data, qualitative research data is rarely available for secondary analysis.

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)0.075
metaresearch head score (Gemma)0.236
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.925
Threshold uncertainty score0.395

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0750.236
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0260.026
Science and technology studies0.0030.004
Scholarly communication0.0070.005
Open science0.0020.006
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0130.002

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.

Opus teacher head0.326
GPT teacher head0.527
Teacher spread0.201 · 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.

Study designTheoretical or conceptual
DomainMethods
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

Citations2
Published2019
Admission routes1
Has abstractyes

Explore more

Same venueInternational journal of open information technologiesSame topicComputational and Text Analysis MethodsFrench-language works237,207