A partir de cette page vous pouvez :
Retourner au premier écran avec les étagères virtuelles... |
Résultat de la recherche
1 résultat(s) recherche sur le mot-clé 'Spam Opinion, Fake Reviews Detection, Semantic Similarity, Corpus based technique, Rule based approach, Tree Based Probability approximation'
Affiner la recherche Faire une suggestion
Detecting Spam Opinion in Online Reviews / Fatima WALID
Titre : Detecting Spam Opinion in Online Reviews Type de document : projet fin études Auteurs : Fatima WALID, Auteur Langues : Français (fre) Catégories : BIG DATA Mots-clés : Spam Opinion, Fake Reviews Detection, Semantic Similarity, Corpus based technique, Rule based approach, Tree Based Probability approximation Index. décimale : mast 264/19 Résumé : Spam (or fake) reviews represent a damaging and a prevalent problem since it is affecting the reliability of both decision making and data analysis of the enterprise as well as the customer’s online experience. The effective identification of spam reviews is a fundamental problem that affects the performance of virtually every application based on review corpus. It’s necessary to develop techniques that can lead business and consumers to distinguish fake from authentic reviews.
In this thesis, we explored two novel approaches that are based on semantic similarity, the first is a rule based technique, using this approach we could reach a 74% accuracy. Then we experienced with tree based probability approximation approach and we have reached 53% accuracy.
Detecting Spam Opinion in Online Reviews [projet fin études] / Fatima WALID, Auteur . - [s.d.].
Langues : Français (fre)
Catégories : BIG DATA Mots-clés : Spam Opinion, Fake Reviews Detection, Semantic Similarity, Corpus based technique, Rule based approach, Tree Based Probability approximation Index. décimale : mast 264/19 Résumé : Spam (or fake) reviews represent a damaging and a prevalent problem since it is affecting the reliability of both decision making and data analysis of the enterprise as well as the customer’s online experience. The effective identification of spam reviews is a fundamental problem that affects the performance of virtually every application based on review corpus. It’s necessary to develop techniques that can lead business and consumers to distinguish fake from authentic reviews.
In this thesis, we explored two novel approaches that are based on semantic similarity, the first is a rule based technique, using this approach we could reach a 74% accuracy. Then we experienced with tree based probability approximation approach and we have reached 53% accuracy.
Réservation
Réserver ce document
Exemplaires
Code barre Cote Support Localisation Section Disponibilité mast 264/19 mast 264/19 FAT Texte imprimé Unité des masters Mast/19 Disponible