FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202045197> ?p ?o ?g. }

• W3202045197 abstract "User generated content such as reviews have a big impact in influencing con- sumer decision on the internet. Several parties are interested in using this platform to achieve their agenda such as profit or many other malicious intention by manu- facturing deceptive opinion spam (Ott et al., 2013). Deceptive opinion spam is the fictitious reviews that have been deliberately written to sound authentic and aims to deceive the reader (Ott et al., 2013). Human detection of deceptive opinion spam is proven to be as low as 57.33% (Ren and Ji, 2017), But research done by Ott et al. (2013) shows the possibility of performing detection using machine learning meth- ods. This research aims to create CNN Ensemble models that implement the concept of using a collection of neural networks by using CNN as the base model to further increase the reliability of the detection model due to the existence of outliers in the base model. The implementation of the CNN Ensemble model consists of 30 CNN model where their individual results is combined to get the CNN Ensemble final re- sult. From the 30 CNN models, 15 of them is using GloVe word embedding while the other 15 models is using FastText word embedding. The individual models start by embedding the reviews to get the numerical representations of the reviews, followed by the convolutional, pooling, and activation layer to get the vector representations of each sentences, and followed by these same layers again to get the vector representa- tions of the whole review. Lastly from these review vector, it is used to get the final prediction of the individual models. The CNN Ensemble model achieve an accuracy of 82%. Finally the CNN Ensemble model experiments using 30 CNNs and 10 CNNs shows that the increasing number of individual model used in the ensemble, without using more individual model variation, would yield insignificant improvements.User generated content such as reviews have a big impact in influencing con- sumer decision on the internet. Several parties are interested in using this platform to achieve their agenda such as profit or many other malicious intention by manu- facturing deceptive opinion spam (Ott et al., 2013). Deceptive opinion spam is the fictitious reviews that have been deliberately written to sound authentic and aims to deceive the reader (Ott et al., 2013). Human detection of deceptive opinion spam is proven to be as low as 57.33% (Ren and Ji, 2017), But research done by Ott et al. (2013) shows the possibility of performing detection using machine learning meth- ods. This research aims to create CNN Ensemble models that implement the concept of using a collection of neural networks by using CNN as the base model to further increase the reliability of the detection model due to the existence of outliers in the base model. The implementation of the CNN Ensemble model consists of 30 CNN model where their individual results is combined to get the CNN Ensemble final re- sult. From the 30 CNN models, 15 of them is using GloVe word embedding while the other 15 models is using FastText word embedding. The individual models start by embedding the reviews to get the numerical representations of the reviews, followed by the convolutional, pooling, and activation layer to get the vector representations of each sentences, and followed by these same layers again to get the vector representa- tions of the whole review. Lastly from these review vector, it is used to get the final prediction of the individual models. The CNN Ensemble model achieve an accuracy of 82%. Finally the CNN Ensemble model experiments using 30 CNNs and 10 CNNs shows that the increasing number of individual model used in the ensemble, without using more individual model variation, would yield insignificant improvements." @default.
• W3202045197 created "2021-10-11" @default.
• W3202045197 creator A5034024306 @default.
• W3202045197 creator A5088413845 @default.
• W3202045197 date "2020-01-01" @default.
• W3202045197 modified "2023-09-27" @default.
• W3202045197 title "DECEPTIVE OPINION SPAM DETECTION USING CONVOLUTIONAL NEURAL NETWORK (CNN) ENSEMBLE" @default.
• W3202045197 hasPublicationYear "2020" @default.
• W3202045197 type Work @default.
• W3202045197 sameAs 3202045197 @default.
• W3202045197 citedByCount "0" @default.
• W3202045197 crossrefType "journal-article" @default.
• W3202045197 hasAuthorship W3202045197A5034024306 @default.
• W3202045197 hasAuthorship W3202045197A5088413845 @default.
• W3202045197 hasConcept C108583219 @default.
• W3202045197 hasConcept C119857082 @default.
• W3202045197 hasConcept C12267149 @default.
• W3202045197 hasConcept C154945302 @default.
• W3202045197 hasConcept C2777462759 @default.
• W3202045197 hasConcept C41008148 @default.
• W3202045197 hasConcept C41608201 @default.
• W3202045197 hasConcept C45942800 @default.
• W3202045197 hasConcept C66402592 @default.
• W3202045197 hasConcept C81363708 @default.
• W3202045197 hasConceptScore W3202045197C108583219 @default.
• W3202045197 hasConceptScore W3202045197C119857082 @default.
• W3202045197 hasConceptScore W3202045197C12267149 @default.
• W3202045197 hasConceptScore W3202045197C154945302 @default.
• W3202045197 hasConceptScore W3202045197C2777462759 @default.
• W3202045197 hasConceptScore W3202045197C41008148 @default.
• W3202045197 hasConceptScore W3202045197C41608201 @default.
• W3202045197 hasConceptScore W3202045197C45942800 @default.
• W3202045197 hasConceptScore W3202045197C66402592 @default.
• W3202045197 hasConceptScore W3202045197C81363708 @default.
• W3202045197 hasLocation W32020451971 @default.
• W3202045197 hasOpenAccess W3202045197 @default.
• W3202045197 hasPrimaryLocation W32020451971 @default.
• W3202045197 hasRelatedWork W2746802549 @default.
• W3202045197 hasRelatedWork W2753983247 @default.
• W3202045197 hasRelatedWork W2767245856 @default.
• W3202045197 hasRelatedWork W2803634114 @default.
• W3202045197 hasRelatedWork W2808195004 @default.
• W3202045197 hasRelatedWork W2808861903 @default.
• W3202045197 hasRelatedWork W2888839716 @default.
• W3202045197 hasRelatedWork W2897565143 @default.
• W3202045197 hasRelatedWork W2909602489 @default.
• W3202045197 hasRelatedWork W2912090347 @default.
• W3202045197 hasRelatedWork W2921304802 @default.
• W3202045197 hasRelatedWork W2996982010 @default.
• W3202045197 hasRelatedWork W3027756743 @default.
• W3202045197 hasRelatedWork W3036519420 @default.
• W3202045197 hasRelatedWork W3085370460 @default.
• W3202045197 hasRelatedWork W3099739484 @default.
• W3202045197 hasRelatedWork W3115558223 @default.
• W3202045197 hasRelatedWork W3137740953 @default.
• W3202045197 hasRelatedWork W3199468579 @default.
• W3202045197 hasRelatedWork W3202814506 @default.
• W3202045197 isParatext "false" @default.
• W3202045197 isRetracted "false" @default.
• W3202045197 magId "3202045197" @default.
• W3202045197 workType "article" @default.