| Naslov: | Beyond aggregate sentiment : machine learning-driven discourse indicators for AI news at scale |
|---|
| Avtorji: | ID Topal, Oleksandra, Institut "Jožef Stefan" (Avtor)
ID Novalija, Inna, Institut "Jožef Stefan" (Avtor)
ID Pita Costa, João, Institut "Jožef Stefan" (Avtor)
ID Roman, Dumitru (Avtor) |
|---|
| Datoteke: |  URL - Izvorni URL, za dostop obiščite https://www.mdpi.com/2673-2688/7/8/307
 PDF - Predstavitvena datoteka, prenos (1,85 MB)
MD5: 91E1F2143ED2E80CA2A7E629E8B2401F
|
|---|
| Jezik: | Angleški jezik |
|---|
| Tipologija: | 1.01 - Izvirni znanstveni članek |
|---|
| Organizacija: |  IJS - Institut Jožef Stefan
|
|---|
| Povzetek: | This study deploys a scalable machine learning pipeline: combining a transformer-based classifier applied to 2.01 million English-language AI-related news headlines (July 2022–July 2024) with large-language-model and human-annotator validation (three annotators, Fleiss’ �=0.80 ) on stratified subsamples, to extract six interpretable, bias-linked discourse indicators computed at the AI-domain level: evaluative orientation (valence), loss salience, narrative drift, exposure-adjusted sentiment, cross-source divergence, and novelty-phase framing. Each operationalizes an established cognitive-psychology construct as a computable property of the information environment associated with biased risk–benefit reasoning. Results show systematic variation across domains: technical and methodological areas such as deep learning and natural language processing exhibit gain-salient framing, while safety-critical topics such as deepfakes (loss-to-gain headline ratio = 3.17) and facial recognition show strongly loss-salient profiles. Cross-model validation using an LLM on a stratified sample of 1000 headlines confirms that domain-level indicator rankings are robust to classifier choice (Spearman �=0.83 ; �<0.001 ), establishing the rank stability of pipeline outputs independently of the specific classification architecture. As a contextual application, domain-level profiles are mapped to European Union AI governance instruments, documenting parallels between discourse patterns and regulatory risk tiers. The framework provides a scalable, reproducible methodology for monitoring evaluative conditions in technology news across domains, sources, and time. |
|---|
| Ključne besede: | applied machine learning, large scale text classification, discourse indicators, transformer-based sentiment analysis, AI-related new headlines, domain-resolved analysis, cross-model validation, large-language models |
|---|
| Status publikacije: | Objavljeno |
|---|
| Verzija publikacije: | Objavljena publikacija |
|---|
| Poslano v recenzijo: | 21.05.2026 |
|---|
| Datum sprejetja članka: | 05.08.2026 |
|---|
| Datum objave: | 07.08.2026 |
|---|
| Založnik: | MDPI |
|---|
| Leto izida: | 2026 |
|---|
| Št. strani: | str. 1-26 |
|---|
| Številčenje: | Vol. 7, issue 8 |
|---|
| Izvor: | Švica |
|---|
| PID: | 20.500.12556/DiRROS-32195  |
|---|
| UDK: | 004.8 |
|---|
| ISSN pri članku: | 2673-2688 |
|---|
| DOI: | /10.3390/ai7080307 |
|---|
| COBISS.SI-ID: | 287986179 |
|---|
| Avtorske pravice: | © 2026 by the authors. |
|---|
| Opomba: | Opis vira z dne 17. 18. 2026;
Nasl. z nasl. zaslona;
Soavtorji: Inna Novalija, Joao Pita Costa, Dumitru Roman;
|
|---|
| Datum objave v DiRROS: | 01.09.2026 |
|---|
| Število ogledov: | 197 |
|---|
| Število prenosov: | 101 |
|---|
| Metapodatki: |    |
|---|
|
:
|
Kopiraj citat |
|---|
| | | | Objavi na: |  |
|---|
Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše
podrobnosti ali sproži prenos. |
