Plateforme d'étiquetage dynamique pour la fouille d'opinion (notice n° 402309)
[ vue normale ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 03018cam a2200337 4500500 |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20250119075257.0 |
| 041 ## - LANGUAGE CODE | |
| Language code of text/sound track or separate title | fre |
| 042 ## - AUTHENTICATION CODE | |
| Authentication code | dc |
| 100 10 - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Reutenauer, Coralie |
| Relator term | author |
| 245 00 - TITLE STATEMENT | |
| Title | Plateforme d'étiquetage dynamique pour la fouille d'opinion |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Date of publication, distribution, etc. | 2014.<br/> |
| 500 ## - GENERAL NOTE | |
| General note | 70 |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | Les plateformes sociales (Twitter, blogs, forums), vecteurs de la diversité des points de vue de la collectivité, constituent un vivier de données convoité pour la fouille d’opinion et l’analyse de sentiments. Dans ce cadre, les méthodes appliquées en classification n’apprennent souvent que des sorties relativement frustes : celles-ci se réduisent à une polarité ou à une gradation linéaire. Est-il possible d’apprendre des motifs plus riches avec un nombre raisonnable d’exemples ? Notre démarche est appliquée au ressenti à l’égard de marques. L’enjeu est d’analyser l’image de marque à l’aide d’un ensemble de traits lexicaux, structurés par leurs relations sémantiques. Pour prédire un tel motif par apprentissage supervisé, il est avant tout nécessaire de disposer d’un jeu de données étiquetées. Pour cela, nous avons mis en place une plateforme collaborative pour l’étiquetage de messages issus du web social en traits sémantiques et sentiments. Afin d’optimiser les étiquetages, la plateforme est sous-tendue par des mécanismes dynamiques à double vocation : filtrer les messages non pertinents et restructurer la grille d’analyse spécifique à chaque marque au fur et à mesure des annotations. |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | Social networks mirror public opinion. As such, they are of great interest for opinion mining and sentiment analysis. In most cases, sentiment is classified according to a polarity criterion or a linear gradation. Is it possible to learn more complex patterns with limited itemsets ? In this article, we investigate brand equity. The goal is to analyse how social groups perceive a given brand. Brand identity is described with a structured set of adjectives, considered as semantic features. Since supervised pattern recognition requires labelled datasets, a platform was set up for social networks sentiment analysis. The platform relies on collaborative and dynamic principles designed to relevance-based filtering and semantic features reconfiguration. |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | apprentissage statistique |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | image de marque |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | classification multi-label |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | annotation |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | IHM |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | analyse de sentiments |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | réseaux sociaux |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | tagging |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | sentiment analysis |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | social networks |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | brand reputation |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | multi-label classification |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | machine learning |
| 700 10 - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Urvoy, Tanguy |
| Relator term | author |
| 786 0# - DATA SOURCE ENTRY | |
| Note | Document numérique | 17 | 1 | 2014-06-01 | p. 85-101 | 1279-5127 |
| 856 41 - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="https://shs.cairn.info/revue-document-numerique-2014-1-page-85?lang=fr&redirect-ssocas=7080">https://shs.cairn.info/revue-document-numerique-2014-1-page-85?lang=fr&redirect-ssocas=7080</a> |
Pas d'exemplaire disponible.
Réseaux sociaux