Personalized movie recommendations based on probabilistic linguistic sentiment and integrated DEMATEL-TODIM methods DOI Creative Commons
Qi Wang,

YinLi You,

Si Wang

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Авг. 27, 2024

With the development of society, online reviews are increasingly becoming a crucial factor in decision-making. Especially for entertainment products such as movies, they preferred their affordability and high factor. Therefore, this paper proposes movie recommendation model that considers user personalization using probabilistic linguistic approach based on reviews. Firstly, method constructs quantitative sentiment framework transforms comments into multi-granular language. Secondly, we build decision-making trial evaluation laboratory (DEMATEL) environments to explore interrelationships between product attributes, improve distance measure score function better integrate information DEMATEL weight calculations. Furthermore, account risk preferences, employs extended TODIM (an acronym Portuguese interactive multicriteria decision making) methodology determine ranking alternatives. Finally, design Douban experiments demonstrate validity model. Compared with other methods, incorporates emotional tendency attributes preference process leading more reasonable results.

Язык: Английский

Intelligent evaluation system for new energy vehicles based on sentiment analysis: An MG-PL-3WD method DOI
Chao Zhang,

Qifei Wen,

Deyu Li

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 133, С. 108485 - 108485

Опубликована: Апрель 25, 2024

Язык: Английский

Процитировано

9

Unstructured Text Data Security Attribute Mining Method Based on Multi‐Model Collaboration DOI Open Access
Xiaohan Wang,

Xuehui Du,

Hengyi Lv

и другие.

Concurrency and Computation Practice and Experience, Год журнала: 2025, Номер 37(3)

Опубликована: Янв. 20, 2025

ABSTRACT Access control is a critical security measure to ensure that sensitive information and resources are accessed only by authorized users. However, attribute‐based access in the big data environment faces challenges such as large number of entity attributes, poor availability, difficulty manual labeling. In this paper, we focus on problem mining optimizing attributes unstructured propose method for textual based multi‐model collaboration. First, utilize unsupervised methods extract candidate from resources, then weight results multiple using rough set theory obtain optimal result. Second, considering various factors including text itself construct feature vector consisting 45 categories represent attributes. Third, employ voting collaboratively train attribute model resources. Finally, HowNet, optimize achieve automated intelligent resource providing an foundation precise control. The experiments indicate precision rate proposed paper can reach up 92.36%, F1‐score 82.51%. scale be compressed 69.59% its original size after optimization. This has greater advantage over other provide support

Язык: Английский

Процитировано

0

A local multi-granularity fuzzy rough set method for multi-attribute decision making based on MOSSO-LSTM and its application in stock market DOI
Juncheng Bai, Bingzhen Sun, Jin Ye

и другие.

Applied Intelligence, Год журнала: 2024, Номер 54(7), С. 5728 - 5747

Опубликована: Апрель 1, 2024

Язык: Английский

Процитировано

3

Modelling customer requirement for mobile games based on online reviews using BW-CNN and S-Kano models DOI
Yanze Liu, Tian‐Hui You, Junrong Zou

и другие.

Expert Systems with Applications, Год журнала: 2024, Номер 258, С. 125142 - 125142

Опубликована: Авг. 24, 2024

Язык: Английский

Процитировано

3

Personalized movie recommendations based on probabilistic linguistic sentiment and integrated DEMATEL-TODIM methods DOI Creative Commons
Qi Wang,

YinLi You,

Si Wang

и другие.

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Авг. 27, 2024

With the development of society, online reviews are increasingly becoming a crucial factor in decision-making. Especially for entertainment products such as movies, they preferred their affordability and high factor. Therefore, this paper proposes movie recommendation model that considers user personalization using probabilistic linguistic approach based on reviews. Firstly, method constructs quantitative sentiment framework transforms comments into multi-granular language. Secondly, we build decision-making trial evaluation laboratory (DEMATEL) environments to explore interrelationships between product attributes, improve distance measure score function better integrate information DEMATEL weight calculations. Furthermore, account risk preferences, employs extended TODIM (an acronym Portuguese interactive multicriteria decision making) methodology determine ranking alternatives. Finally, design Douban experiments demonstrate validity model. Compared with other methods, incorporates emotional tendency attributes preference process leading more reasonable results.

Язык: Английский

Процитировано

1