Due to the increasing importance of online product reviews,how to accurately identify fake reviews has become an issue of concern to enterprises and consumers.The contextual features encapsulate the semantic informati...Due to the increasing importance of online product reviews,how to accurately identify fake reviews has become an issue of concern to enterprises and consumers.The contextual features encapsulate the semantic information of review,while the behavioral features reflect the behavioral patterns of reviewers.However,an appropriate method to integrate contextual and behavioral features is a challenging task,hence an end-to-end model based on Weighted Fusion of Contextual Features and Reviewer Behaviors(WF-CFRB)for fake review detection is proposed.Firstly,the categories of average cosine similarity and the corpus of review are jointly fed into BERT to obtain contextual feature vectors.Then,the underlying patterns of the reviewer behaviors are extracted by CNN to construct behavioral feature vectors.Finally,a weighted fusion method is adopted to fuse contextual and behavior features for fake review detection.WF-CFRB and each component are evaluated on YELP dataset.WF-CFRB achieves F1 score of 81.31%and AUC score of 81.27%,and it also outperforms the other baseline models in terms of accuracy and recall.Compared with the original BERT model,the experimental results indicate that cosine similarity provides BERT with more information,which is useful to construct the contextual feature vectors.Through the weighted fusion of contextual and behavioral features,WF-CFRB yields excellent performance on fake review detection,which is particularly suitable for scenarios where behavioral features can be captured.展开更多
With the recent increase in data volume and diversity,traditional text representation techniques are struggling to capture context,particularly in environments with sparse data.To address these challenges,this study p...With the recent increase in data volume and diversity,traditional text representation techniques are struggling to capture context,particularly in environments with sparse data.To address these challenges,this study proposes a new model,the Masked Joint Representation Model(MJRM).MJRM approximates the original hypothesis by leveraging multiple elements in a limited context.It dynamically adapts to changes in characteristics based on data distribution through three main components.First,masking-based representation learning,termed selective dynamic masking,integrates topic modeling and sentiment clustering to generate and train multiple instances across different data subsets,whose predictions are then aggregated with optimized weights.This design alleviates sparsity,suppresses noise,and preserves contextual structures.Second,regularization-based improvements are applied.Third,techniques for addressing sparse data are used to perform final inference.As a result,MJRM improves performance by up to 4%compared to existing AI techniques.In our experiments,we analyzed the contribution of each factor,demonstrating that masking,dynamic learning,and aggregating multiple instances complement each other to improve performance.This demonstrates that a masking-based multi-learning strategy is effective for context-aware sparse text classification,and can be useful even in challenging situations such as data shortage or data distribution variations.We expect that the approach can be extended to diverse fields such as sentiment analysis,spam filtering,and domain-specific document classification.展开更多
The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study s...The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study super-resolution(SR)algorithms applied to CT images to improve the reso-lution of CT images.However,most of the existing SR algorithms are studied based on natural images,which are not suitable for medical images;and most of these algorithms improve the reconstruction quality by increasing the network depth,which is not suitable for machines with limited resources.To alleviate these issues,we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution(RFAFN).Specifically,we design a contextual feature extraction block(CFEB)that can extract CT image features more efficiently and accurately than ordinary residual blocks.In addition,we propose a feature-weighted cascading strategy(FWCS)based on attentional feature fusion blocks(AFFB)to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information.Finally,we suggest a global hierarchical feature fusion strategy(GHFFS),which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels.Numerous experiments show that our method performs better than most of the state-of-the-art(SOTA)methods on the COVID-19 chest CT dataset.In detail,the peak signal-to-noise ratio(PSNR)is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at×3 SR compared to the suboptimal method,but the number of parameters and multi-adds are reduced by 22K and 0.43G,respectively.Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.展开更多
基金supported by National Key Research and Development Program Project“Research on data-driven comprehensive quality accurate service technology for small medium and micro enterprises”under Grant No.2019YFB1405303the Project of Cultivation for Young Top-motch Talents of Beijing Municipal Institutions“Research on the comprehensive quality intelligent service and optimized technology for small medium and micro enterprises”under Grant No.BPHR202203233National Natural Science Foundation of China“Research on the influence and governance strategy of online review manipulation with the perspective of E-commerce ecosystem”under Grant No.72174018.
文摘Due to the increasing importance of online product reviews,how to accurately identify fake reviews has become an issue of concern to enterprises and consumers.The contextual features encapsulate the semantic information of review,while the behavioral features reflect the behavioral patterns of reviewers.However,an appropriate method to integrate contextual and behavioral features is a challenging task,hence an end-to-end model based on Weighted Fusion of Contextual Features and Reviewer Behaviors(WF-CFRB)for fake review detection is proposed.Firstly,the categories of average cosine similarity and the corpus of review are jointly fed into BERT to obtain contextual feature vectors.Then,the underlying patterns of the reviewer behaviors are extracted by CNN to construct behavioral feature vectors.Finally,a weighted fusion method is adopted to fuse contextual and behavior features for fake review detection.WF-CFRB and each component are evaluated on YELP dataset.WF-CFRB achieves F1 score of 81.31%and AUC score of 81.27%,and it also outperforms the other baseline models in terms of accuracy and recall.Compared with the original BERT model,the experimental results indicate that cosine similarity provides BERT with more information,which is useful to construct the contextual feature vectors.Through the weighted fusion of contextual and behavioral features,WF-CFRB yields excellent performance on fake review detection,which is particularly suitable for scenarios where behavioral features can be captured.
基金supported by the SungKyunKwan University and the BK21 FOUR(Graduate School Innovation)funded by the Ministry of Education(MOE,Korea)and National Research Foundation of Korea(NRF).
文摘With the recent increase in data volume and diversity,traditional text representation techniques are struggling to capture context,particularly in environments with sparse data.To address these challenges,this study proposes a new model,the Masked Joint Representation Model(MJRM).MJRM approximates the original hypothesis by leveraging multiple elements in a limited context.It dynamically adapts to changes in characteristics based on data distribution through three main components.First,masking-based representation learning,termed selective dynamic masking,integrates topic modeling and sentiment clustering to generate and train multiple instances across different data subsets,whose predictions are then aggregated with optimized weights.This design alleviates sparsity,suppresses noise,and preserves contextual structures.Second,regularization-based improvements are applied.Third,techniques for addressing sparse data are used to perform final inference.As a result,MJRM improves performance by up to 4%compared to existing AI techniques.In our experiments,we analyzed the contribution of each factor,demonstrating that masking,dynamic learning,and aggregating multiple instances complement each other to improve performance.This demonstrates that a masking-based multi-learning strategy is effective for context-aware sparse text classification,and can be useful even in challenging situations such as data shortage or data distribution variations.We expect that the approach can be extended to diverse fields such as sentiment analysis,spam filtering,and domain-specific document classification.
基金supported by the General Project of Natural Science Foundation of Hebei Province of China(H2019201378)the Foundation of the President of Hebei University(XZJJ201917)the Special Project for Cultivating Scientific and Technological Innovation Ability of University and Middle School Students of Hebei Province(2021H060306).
文摘The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study super-resolution(SR)algorithms applied to CT images to improve the reso-lution of CT images.However,most of the existing SR algorithms are studied based on natural images,which are not suitable for medical images;and most of these algorithms improve the reconstruction quality by increasing the network depth,which is not suitable for machines with limited resources.To alleviate these issues,we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution(RFAFN).Specifically,we design a contextual feature extraction block(CFEB)that can extract CT image features more efficiently and accurately than ordinary residual blocks.In addition,we propose a feature-weighted cascading strategy(FWCS)based on attentional feature fusion blocks(AFFB)to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information.Finally,we suggest a global hierarchical feature fusion strategy(GHFFS),which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels.Numerous experiments show that our method performs better than most of the state-of-the-art(SOTA)methods on the COVID-19 chest CT dataset.In detail,the peak signal-to-noise ratio(PSNR)is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at×3 SR compared to the suboptimal method,but the number of parameters and multi-adds are reduced by 22K and 0.43G,respectively.Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.
