检索结果-内蒙古大学图书馆

Traditional Machine Learning Models and bidirectional encoder representations from transformer (BERT)-Based Automatic Classification of Tweets About Eating Disorders: Algorithm Development and Validation Study

引用

JMIR Medical Informatics 2022年第2期10卷 e34492页

作者： Benítez-Andrades, Jose Alberto Alija-Perez, Jose-Manuel Vidal, Maria-Esther Pastor-Vargas, Rafael García-Ordas, María Teresa SALBIS Research Group Department of Electric Systems and Automatics Engineering University of Leon Leon Spain SECOMUCI Research Group Escuela de Ingenierías Industrial e Informática Universidad de Leon Leon Spain Leibniz University of Hannover Hannover Germany Communications and Control Systems Department Spanish National University for Distance Education Madrid Spain

Background: Eating disorders affect an increasing number of people. Social networks provide information that can help. Objective: We aimed to find machine learning models capable of efficiently categorizing tweets about eating disorders domain. Methods: We collected tweets related to eating disorders, for 3 consecutive months. After preprocessing, a subset of 2000 tweets was labeled: (1) messages written by people suffering from eating disorders or not, (2) messages promoting suffering from eating disorders or not, (3) informative messages or not, and (4) scientific or nonscientific messages. Traditional machine learning and deep learning models were used to classify tweets. We evaluated accuracy, F1 score, and computational time for each model. Results: A total of 1,058,957 tweets related to eating disorders were collected. were obtained in the 4 categorizations, with The bidirectional encoder representations from transformer-based models had the best score among the machine learning and deep learning techniques applied to the 4 categorization tasks (F1 scores 71.1%-86.4%). Conclusions: bidirectional encoder representations from transformer-based models have better performance, although their computational cost is significantly higher than those of traditional techniques, in classifying eating disorder-related tweets. © 2022 JMIR Publications Inc.. All right reserved.

关键词： BERT bidirectional encoder representations from transformer classification data deep learning diet disorder eating disorder machine learning mental health model natural language processing NLP nutrition performance social media Twitter weight

来源：评论

学校读者我要写书评

暂无评论

Reciprocating encoder Portrayal from Reliable transformer Dependent bidirectional Long Short-Term Memory for Question and Answering Text Classification

引用

IEEE ACCESS 2024年 12卷 117800-117811页

作者： Suguna, M. Prabha, K. S. Sakunthala Vellore Inst Technol Sch Comp Sci & Engn Chennai 600127 India

Diversity in use of Question and Answering (Q/A) is evolving as a popular application in the area of Natural Language Processing (NLP). The alive unsupervised word embedding approaches are efficient to collect Latent-Semantic data on number of tasks. But certain methods are still unable to tackle issues such as polysemous-unaware with task-unaware phenomena in NLP tasks. GloVe understands word embedding by availing information statistics from word co-occurrence matrices. Nevertheless, word-pairs in the matrices are taken from a pre-established window of local context, which may result in constrained word-pairs and also probably semantic inappropriate word-pairs. SemGloVe employed in this paper, refines semantic co-occurrences from BERT into static GloVe word-embedding with bidirectional-Long-Short-Term-Memory (BERT- Bi-LSTM) model for text categorization in Q/A. This method utilizes the CR23K and CR1000k datasets for the effective text classification of NLP. The proposed model, with SemGloVe Embedding on BERT combined with Bi-LSTM, produced better results on metrics like accuracy, precision, recall, and F1 Score as 0.92, 0.79, 0.85, and 0.73, respectively, when compared to existing methods of Text2GraphQL, GPT-2, BERT and SPARQL. The BERT model with Bi-LSTM is better in every way for responding to different kinds of questions.

关键词： bidirectional encoder representations from transformer natural language processing question and answering SemGloVe bidirectional encoder representations from transformer natural language processing question and answering SemGloVe

来源：评论

学校读者我要写书评

暂无评论

Utilization of Generative AI and Natural Language Processing for the Extraction of the Voice of Customers from Online Product Reviews

引用

HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES 2025年 15卷

作者： Byun, Jeongeun Seo, Sumin Bae, Kuk Jin Korea Inst Sci & Technol Informat KISTI Res Ctr Technol Commercializat Seoul South Korea

Product life cycles continue to shorten with the rapid pace of technological innovation and intensifying global competition. This escalation in speed, quality, and cost demands for new product development can be met by quickly identifying and reflecting customer requirements (CRs) based on quality function deployment (QFD). This study presents a new approach to overcome the limitations of the traditional qualitative methods in QFD by utilizing large-scale online product review data, considering the importance, topics, and context to apply optimal natural language processing techniques. Extracting CRs using term frequency-inverse document frequency (TF-IDF), topic modeling, and bidirectional encoder representations from transformers (BERT), followed by summarizing the extracted CRs into sentences using generative artificial intelligence, enables a more precise analysis of online product review data without human intervention. This approach allows for the swift and accurate incorporation of CRs into product development. Implementing a review-specialized BERT, which understands the characteristics of review language, showed superior multi-class classification performance by at least 1% across all aspects-precision, recall, F1-score, and accuracy-compared to the base BERT.

关键词： Natural Language Processing bidirectional encoder representations from transformer Generative Artificial Intelligence Quality Function Deployment Voice of the Customer

来源：评论

学校读者我要写书评

暂无评论

Improving Systematic Review Updates With Natural Language Processing Through Abstract Component Classification and Selection: Algorithm Development and Validation

引用

JMIR MEDICAL INFORMATICS 2025年 13卷 e65371页

作者： Hasegawa, Tatsuki Kizaki, Hayato Ikegami, Keisho Imai, Shungo Yanagisawa, Yuki Yada, Shuntaro Aramaki, Eiji Hori, Satoko Keio Univ Fac Pharm Div Drug Informat 1-5-30 ShibakoenMinato Ku Tokyo 1058512 Japan Nara Inst Sci & Technol Nara Japan Univ Tsukuba Fac Lib Informat & Media Sci Tsukuba Japan

Background: A challenge in updating systematic reviews is the workload in screening the articles. Many screening models using natural language processing technology have been implemented to scrutinize articles based on titles and abstracts. While these approaches show promise, traditional models typically treat abstracts as uniform text. We hypothesize that selective training on specific abstract components could enhance model performance for systematic review screening. Objective: We evaluated the efficacy of a novel screening model that selects specific components from abstracts to improve performance and developed an automatic systematic review update model using an abstract component classifier to categorize abstracts based on their components. Methods: A screening model was created based on the included and excluded articles in the existing systematic review used as the scheme for the automatic update of the systematic review. A prior publication was selected for the systematic review, and articlesincluded or excluded in the articles screening process were used as training data. Thetitles and abstracts were classified into 5 categories (Title, Introduction, Methods, Results, and Conclusion). Thirty-one component-composition datasets created by combining 5 component datasets. We implemented 31 screening models using the component-composition datasets and compared their performances. Comparisons were conducted using 3 pretrained models: bidirectional encoder representations from transformer (BERT), BioLinkBERT, and BioM-Efficiently Learning an encoder that Classifies Token Replacements Accurately (ELECTRA). Moreover, to automate the component selection of abstracts, we developed the Abstract Component Classifier Model and created component datasets using this classifier model classification. Using the component datasets classified using the Abstract Component Classifier Model, we created 10 component-composition datasets used by the top 10 screening models with t

关键词： systematic review natural language processing guideline updates bidirectional encoder representations from transformer screening model literature efficiency updating systematic reviews language model

来源：评论

学校读者我要写书评

暂无评论

Multimodal Abstractive Summarization using bidirectional encoder representations from transformers with attention mechanism

引用

HELIYON 2024年第4期10卷 e26162页

作者： Argade, Dakshata Khairnar, Vaishali Vora, Deepali Patil, Shruti Kotecha, Ketan Alfarhood, Sultan Terna Engn Coll Navi Mumbai 400706 India Symbiosis Inst Technol Deemed Univ Symbiosis Int Technol Pune Campus Pune 412115 India Symbiosis Int Deemed Univ SIU Symbiosis Inst Technol Pune Campus Symbiosis Ctr Appl Artificial Intelligence SCAAI Pune 412115 India King Saud Univ Coll Comp & Informat Sci Dept Comp Sci POB 51178 Riyadh 51178 Saudi Arabia

In recent decades, abstractive text summarization using multimodal input has attracted many researchers due to the capability of gathering information from various sources to create a concise summary. However, the existing methodologies based on multimodal summarization provide only a summary for the short videos and poor results for the lengthy videos. To address the aforementioned issues, this research presented the Multimodal Abstractive Summarization using bidirectional encoder representations from transformers (MAS-BERT) with an attention mechanism. The purpose of the video summarization is to increase the speed of searching for a large collection of videos so that the users can quickly decide whether the video is relevant or not by reading the summary. Initially, the data is obtained from the publicly available How2 dataset and is encoded using the bidirectional Gated Recurrent Unit (Bi-GRU) encoder and the Long Short Term Memory (LSTM) encoder. The textual data which is embedded in the embedding layer is encoded using a bidirectional GRU encoder and the features with audio and video data are encoded with LSTM encoder. After this, BERT based attention mechanism is used to combine the modalities and finally, the BI-GRU based decoder is used for summarizing the multimodalities. The results obtained through the experiments that show the proposed MAS-BERT has achieved a better result of 60.2 for Rouge-1 whereas, the existing Decoder-only Multimodal transformer (DMmT) and the Factorized Multimodal transformer based Decoder Only Language model (FLORAL) has achieved 49.58 and 56.89 respectively. Our work facilitates users by providing better contextual information and user experience and would help video-sharing platforms for customer retention by allowing users to search for relevant videos by looking at its summary.

关键词： Attention mechanism bidirectional encoder representations from transformer Decoder encoder Multimodalities Multimodal abstractive summarization

来源：评论

学校读者我要写书评

暂无评论

Chinese Named Entity Recognition of Epidemiological Investigation of Information on COVID-19 Based on BERT

引用

IEEE ACCESS 2022年 10卷 104156-104168页

作者： Yang, Chongluo Sheng, Long Wei, Zhongcheng Wang, Wei Hebei Univ Engn Sch Informat & Elect Engn Handan 056038 Hebei Peoples R China Hebei Univ Engn Hebei Key Lab Secur Protect Informat Sensing & Pr Handan 056038 Hebei Peoples R China

The named entity recognition based on the epidemiological investigation of information on COVID-19 can help analyze the source and route of transmission of the epidemic to control the spread of the epidemic better. Therefore, this paper proposes a Chinese named entity recognition model BERT-BiLSTM-IDCNN-ELU-CRF (BBIEC) based on the epidemiological investigation of information on COVID-19 of the BERT pre-training model. The model first processes the unlabeled epidemiological investigation of information on COVID-19 into the character-level corpus and annotates it with artificial entities according to the BIOES character-level labeling system and then uses the BERT pre-training model to obtain the word vector with position information;then, through the bidirectional long-short term memory neural network (BiLSTM) and the improved iterated dilated convolutional neural network (IDCNN) extract global context and local features from the generated word vectors and concatenate them serially;output all possible label sequences to the conditional random field (CRF);finally pass the condition random The airport decodes and generates the entity tag sequence. The experimental results show that the model is better than other traditional models in recognizing the entity of the epidemiological investigation of information on COVID-19.

关键词： COVID-19 Feature extraction Bit error rate Hidden Markov models Biological system modeling Encoding Text recognition Long short term memory Chinese named entity recognition the epidemiological investigation of information on COVID-19 bidirectional encoder representations from transformer bidirectional long-short term memory network iterated dilated convolutional neural network conditional random field

来源：评论

学校读者我要写书评

暂无评论

A Kernel-Based Real-Time Adaptive Dynamic Programming Method for Economic Household Energy Systems

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2023年第3期19卷 2374-2384页

作者： Yuan, Jun Chen, Si-Zhe Yu, Samson S. S. Zhang, Guidong Chen, Zhe Zhang, Yun Guangdong Univ Technol Sch Automat Guangzhou 510006 Guangdong Peoples R China Deakin Univ Sch Engn Waurn Ponds Vic 3216 Australia Aalborg Univ Fac Engn & Sci DK-9220 Aalborg Denmark

Modern home energy management systems (HEMSs) have great flexibility of energy consumption for customers, but at the same time, bear a range of problems, such as the high system complexity, uncertainty and time-varying nature of load consumptions, and renewable sources generation. This has brought great challenges for the real-time control. To solve these problems, we propose an HEMS that integrates a kernel-based real-time adaptive dynamic programming (K-RT-ADP) with a new preprocessing short-term prediction technique. For the preprocessing short-term prediction, we propose a gated recurrent unit-bidirectional encoder representations from the transformer (GRU-BERT) model to improve the forecasting accuracy of electrical loads and renewable energy generation. In particular, we classify household appliances into the temperature-sensitive loads, human activity sensitive loads, and insensitive/constant loads. The GRU-BERT model can incorporate weather and human activity information to predict load consumption and solar generation. For real-time control, we propose and employ the K-RT-ADP HEMS based on the GRU-BERT prediction algorithm. The objective of the K-RT-ADP HEMS is to minimize the electricity cost and maximize the solar energy utilization. To enhance the nonlinear approximation ability and generalization ability of the adaptive dynamic programming (ADP) algorithm, the K-RT-ADP algorithm leverages kernel mapping instead of neural networks. Hardware-in-the-loop experiments demonstrate the superiority of the proposed K-RT-ADP HEMS over the traditional ADP control through comparison.

关键词： Prediction algorithms Approximation algorithms Real-time systems Artificial neural networks Kernel Batteries Renewable energy sources bidirectional encoder representations from transformer home energy management system (HEMS) kernel-based adaptive dynamic programming (ADP)

来源：评论

学校读者我要写书评

暂无评论

Fake content detection on benchmark dataset using various deep learning models

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL SCIENCE AND ENGINEERING 2024年第5期27卷 570-581页

作者： Thaokar, Chetana Rout, Jitendra Kumar Das, Himansu Rout, Minakhi KIIT Univ Sch Comp Engn Bhubaneswar India Ramdeobaba Coll Engn & Management Dept Informat Technol Nagpur India Natl Inst Technol Raipur Dept Comp Sci & Engn Raipur India

The widespread use of social media and its development have offered a medium for the propagation of fake contents quickly among the masses. Fake contents frequently misguide individuals and lead to erroneous social judgments. Individuals and society have been harmed by the dissemination of low-quality news content on social media. In this paper, we have worked on a benchmark dataset of news content and proposed an approach comprising basic natural language processing techniques with different deep learning models for categorising content as real or fake. Different deep learning models employed are LSTM, bi-LSTM, LSTM and bi-LSTM with an attention mechanism. We compared the outcomes by using one hot word embedding and pre-trained GloVe technique. On benchmark LIAR dataset, the LSTM achieved a better accuracy of 67.2%, while the bi-LSTM with GloVe word embedding reached an accuracy of 67%. An accuracy of 98.22% is achieved using bi-LSTM and 97.98% using LSTM on Real-Fake dataset. Fake news can be a menace to society, so if it is detected early, harmony can be maintained in society and individuals can avoid being misled.

关键词： fake news word embedding global vectors GloVe LIAR dataset deep learning models bidirectional encoder representations from transformer BERT

来源：评论

学校读者我要写书评

暂无评论

GSAM: A deep neural network model for extracting computational representations of Chinese addresses fused with geospatial feature

引用

COMPUTERS ENVIRONMENT AND URBAN SYSTEMS 2020年 81卷 101473-000页

作者： Xu, Liuchang Du, Zhenhong Mao, Ruichen Zhang, Feng Liu, Renyi Zhejiang Univ Sch Earth Sci 38 Zheda RdXixi Campus Hangzhou 310027 Zhejiang Peoples R China Zhejiang Prov Key Lab Geog Informat Sci 148 Tianmushan Rd Hangzhou 310028 Peoples R China

Addresses are one of the most important geographical reference systems in natural languages. In China, due to the relatively backward address planning, there are a large number of non-standard addresses. This kind of unstructured text makes the management and application of Chinese addresses much more difficult. However, by extracting the computational representations of addresses, it can be structured and its related applications can be extended more conveniently. Therefore, this paper utilizes a deep neural language model from natural language processing (NLP) to automatically extract computational representations through an unsupervised address language model (ALM), which is trained in an unsupervised way and is suitable for a large-scale address corpus. We propose a solution to fuse addresses and geospatial features and construct a geospatial-semantic address model (GSAM) that supports a variety of downstream tasks. Our proposed GSAM constructing process consists of three phases. First, we build an ALM using bidirectional encoder representations from transformers (BERT) to learn the addresses' semantic representations. Then, the fusion clustering results of the semantic and geospatial information are obtained by a high-dimensional clustering algorithm. Finally, we construct the GSAM based on the fused clustering results using novel fine-tuning techniques. Furthermore, we apply the extracted computational representation from GSAM to the address location prediction task. The experimental results indicate that the target task accuracy of the ALM is 90.79%, and the result of semantic geospatial fusion clustering strongly correlates with fine-grained urban neighbourhood area division. The GSAM can accurately identify clustering labels and the values of evaluation metrics are all above 0.96. We also demonstrate that our model outperforms purely ALM-based and word2vec-based models by address location prediction task.

关键词： Chinese addresses Computational representations Semantic/geospatial fusion bidirectional encoder representations from transformer Feature fusion clustering Address location prediction task

来源：评论

学校读者我要写书评

暂无评论

Domain Effect Investigation for Bert Models Fine-Tuned on Different Text Categorization Tasks

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2024年第3期49卷 3685-3702页

作者： Coban, Onder Yaganoglu, Mete Bozkurt, Ferhat Ataturk Univ Dept Comp Engn Fac Engn Erzurum Turkiye

Text categorization (TC) is one of the most useful automatic tools in today's world to organize huge text data automatically. It is widely used by practitioners to classify texts automatically for different purposes, including sentiment analysis, authorship detection, spam detection, and so on. However, studying TC task for different fields can be challenging since it is required to train a separate model on a labeled and large data set specific to that field. This is very time-consuming, and creating a domain-specific large and labeled data is often very hard. In order to overcome this problem, language models are recently employed to transfer learned information from a large data to another downstream task. bidirectional encoder representations from transformer (BERT) is one of the most popular language models and has been shown to provide very good results for TC tasks. Hence, in this study, we use four pretrained BERT models trained on formal text data as well as our own BERT models trained on Facebook messages. We then fine-tuned BERT models on different downstream data sets collected from different domains such as Twitter, Instagram, and so on. We aim to investigate whether fine-tuned BERT models can provide satisfying results on different downstream tasks of different domains via transfer learning. The results of our extensive experiments show that BERT models provide very satisfying results and selecting both the BERT model and downstream tasks' data from the same or similar domain is akin to improve the performance in a further direction. This shows that a well-trained language model can remove the need for a separate training process for each different downstream TC task within the OSN domain.

关键词： User-generated content Text categorization Deep learning bidirectional encoder representations from transformer

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：