Article
Mathematics, Interdisciplinary Applications
Lei Shi, Yulin Zhu, Youpeng Zhang, Zhongji Su
Summary: This study utilizes natural language processing method, extracting semantic features of text using Latent Dirichlet Allocation (LDA) topic model and constructing a signal equipment fault diagnostic model with Support Vector Machine (SVM) algorithm, demonstrating the effectiveness of fault diagnosis for high-speed railway signal equipment.
Article
Computer Science, Artificial Intelligence
Ming Chen, Tianyi Ma, Xiuze Zhou
Summary: In collaborative filtering, we propose a novel neural network, CoCNN, which combines co-occurrence patterns and CNN to improve performance using implicit feedback. The co-occurrence pattern identifies items that consistently appear between pairs on a user's favorite list. By establishing co-occurrence relationships, we successfully capture more useful information.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Dongbin He, Yanzhao Ren, Abdul Mateen Khattak, Xinliang Liu, Sha Tao, Wanlin Gao
Summary: This study introduced a novel two-phase neural embedding framework with redundancy-aware sorting process to optimize topic labeling, improve the effectiveness of the labeling system, and discover more meaningful topic labels.
Article
Public, Environmental & Occupational Health
Suishan Gu, Kangyu Wang, Lianyue Gao, Jun Liu
Summary: This paper constructs a defect evaluation model for express service and proposes improvement directions. It is found that responsiveness defect needs the most improvement.
FRONTIERS IN PUBLIC HEALTH
(2022)
Article
Computer Science, Theory & Methods
Ming Chen, Yunhao Li, Xiuze Zhou
Summary: The CoNet neural network effectively models item co-occurrence patterns in collaborative filtering, leading to superior performance compared to existing methods.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Telecommunications
Jin Xie, Fuxi Zhu, Huanmei Guan, Jiangqing Wang, Hao Feng, Lin Zheng
Summary: The study improved the LDA model and designed the SFM model based on collaborative filtering, which can capture query intent more accurately and improve the quality of user recommendations.
CHINA COMMUNICATIONS
(2021)
Article
Multidisciplinary Sciences
Yilan Qi, Jun He
Summary: This paper proposes an off-topic detection algorithm by combining LDA and word2vec, which solves the accuracy and efficiency problems in off-topic detection of English compositions. The algorithm models and trains the document using the LDA model and word2vec, calculates the probability weighted sum for each topic and its feature words based on the semantic relationship between topics and words, and selects off-topic compositions by setting a reasonable threshold. Experimental results show that this method is more effective than the vector space model, capable of detecting more off-topic compositions with higher accuracy.
Article
Chemistry, Multidisciplinary
Dante Conti, Carlos Eduardo Gomez, Juan Guillermo Jaramillo, Victoria Eugenia Ospina
Summary: The research aims to analyze service perception in public sector companies in Bogota using Twitter and text mining. By implementing data modeling and analyzing sentiment evolution, the study identifies areas, problems, and topics for improvement. The LDA algorithm helps visualize the most negatively impactful topics reported by users over different time periods.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Qiuqing Meng, Huixiang Xiong
Summary: Doctor recommendation technology utilizes a hybrid model and graph computing methods to help patients quickly and accurately find doctors who meet their actual needs based on consultation information, providing helpful personalized online healthcare services.
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Andrea Zielinski
Summary: This paper presents a systematic analysis of the computation of the text-based Rao index, based on probabilistic topic models. The study compares the classical LDA model with a neural network topic model. The results show that parameter variations significantly affect the topic model-based Rao metrics, and topic models that yield semantically cohesive topics result in more stable measurements of the Rao index.
Article
Operations Research & Management Science
Hikaru Goto, H. M. Belal, Kunio Shirahada
Summary: This study identifies 12 types of value co-destruction (VCD) in healthcare services, based on complaints from dental clinic patients. Ten antecedents of these VCD types are also identified, with institutional factors and social norms found to be related to the VCD process. The study contributes to understanding failures in healthcare services and developing effective decision making.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Computer Science, Software Engineering
Guosheng Kang, Yong Xiao, Jianxun Liu, Yingcheng Cao, Buqing Cao, Xiangping Zhang, Linghang Ding
Summary: This paper proposes a new Web service classification method that combines BiLSTM and HDP with attention mechanism to enhance feature representation and improve classification accuracy. Extensive experiments validate the effectiveness of the proposed approach.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2021)
Article
Computer Science, Information Systems
Qin Liang, Chunchun Hu, Si Chen
Summary: Researchers proposed an evaluation method combining a pre-training model and topic model to determine the optimal topic classification number based on semantic similarity. In an empirical study using COVID-19 as an example, they successfully generated five categories of public opinion topics and found their spatial and temporal distribution patterns consistent with the epidemic development.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Computer Science, Information Systems
Thanh Trinh, Dingming Wu, Ruili Wang, Joshua Zhexue Huang
Summary: This study proposes a new method to recommend events to the top N active-friends of a key user in EBSNs, by constructing an association matrix and defining a content-based event recommendation model. Experiments conducted on real datasets from Meetup have shown the effectiveness of the new model.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Wei Zeng, Jiwei Qin, Chunting Wei
Summary: This paper proposes a collaborative filtering model based on implicit trust relationships, combining implicit trust information and user-item interaction behavior to address information overload in recommendation systems. By integrating user co-occurrence matrix embedding and collaborative neural recommendation, the NCAR model improves recommendation accuracy, as demonstrated by experiments on four public datasets.