检索结果-内蒙古大学图书馆

Identification and analysis of driving factors for product evolution: A text data mining approach

ALEXANDRIA ENGINEERING JOURNAL 2025年 126卷 143-159页

作者： Liu, Shifeng Su, Jianning Zhang, Shutao Qiu, Kai Wang, Shijie Lanzhou Univ Technol Sch Mech & Elect Engn Lanzhou 730050 Peoples R China Lanzhou Univ Technol Sch Design Art Lanzhou 730050 Peoples R China

Products continuously evolve over time as a result of changes in various factors, including technological advancements, customer requirements, and material processes. The complexity and interconnections among these factors present significant challenges for their identification and description. Traditional studies primarily rely on inductive summarization, which often faces issues of subjectivity, uncertainty, and low reliability. This research presents a method combining the Bidirectional Encoder Representations from Transformers (BERT) model and Dynamic Topic Model (DTM) to analyze the driving factors of product evolution. First, the BERT model was employed to enhance the DTM model, and a text corpus related to product evolution was constructed to identify its driving factors. Then, similar algorithms and co-occurrence network analysis methods are applied to study the spatiotemporal evolution of these driving factors at different granular levels and their impact on designers' cognition. Finally, a case study on the evolution of automobiles is conducted to verify the effectiveness and applicability of the proposed model. The results indicate that incorporating the BERT model to enhance the DTM model improves semantic extraction from textual data. Moreover, significant interdependencies were identified among the driving factors, with their specific meanings progressively evolving towards domains such as human emotions, culture, and experiences. From a data mining perspective, this approach addresses the challenges of identifying product evolution driving factors, assisting designers and decision-makers in executing iterative product development more efficiently and scientifically.

关键词： Product evolution Driving factor DTM BERT text data

来源：评论

学校读者我要写书评

暂无评论

Towards Reliable Drift Detection and Explanation in text data 25th

Towards Reliable Drift Detection and Explanation in Text Dat...

引用

25th International Conference on Intelligent data Engineering and Automated Learning

作者： Feldhans, Robert Hammer, Barbara Bielefeld Univ Bielefeld Germany

ISBN: (纸本)9783031777301;9783031777318

When delivered to the market, machine learning models face new data which are possibly subject to novel characteristics - a phenomenon known as concept drift. As this might lead to performance degradation, it is necessary to detect such drift and, if required, adapt the model accordingly. While a variety of drift detection and adaptation methods exists for standard vectorial data, a suitable treatment of text data is less researched. In this work we present a novel approach which detects and explains drift in text data based on their representation via transformer embeddings. In a nutshell, the method generates suitable statistical features from the original distribution and the possibly shifted variation. Based on these representations, drift scores can be assigned to individual data points, allowing a visualization and human-readable characterization of the type of drift. We demonstrate the approach's effectiveness in reliably detecting drift in several experiments.

关键词： Drift Explanation text data Transformer Visualization

来源：评论

学校读者我要写书评

暂无评论

A comprehensive review of current trends, challenges, and opportunities in text data privacy

引用

COMPUTERS & SECURITY 2025年 151卷

作者： Shahriar, Sakib Dara, Rozita Akalu, Rajen Univ Guelph Sch Comp Sci 50 Stone Rd E Guelph ON N1G 2W1 Canada Univ Ontario Inst Technol Fac Business & Informat Technol Oshawa ON Canada

The emergence of smartphones and internet accessibility around the globe have enabled billions of people to be connected to the digital world. Due to the popularity of instant messaging applications and social media, a large quantity of personal data is in text format, and processing text data in a privacy-preserving manner poses unique challenges. While existing reviews focus on privacy concerns from specific algorithmic perspectives or target only a particular domain, such as healthcare or smart metering, they fail to provide a comprehensive view that addresses the multi-layered privacy risks inherent to text data processing. Existing works often limit their scope to specialized solutions like differential privacy, anonymization, or federated learning, neglecting a broader spectrum of challenges. To fill this gap, we present a comprehensive review of privacy-enhancing solutions for text data processing in the present literature and classify the works into six categories of privacy risks: (i) unintentional memorability, (ii) membership inference, (iii) exposure and re-identification, (iv) language models and word embeddings, (v) authorship attribution, and (vi) collaborative processing. We then analyze existing privacy-enhancing solutions for text data by considering the aforementioned privacy risks. Finally, we identified several research gaps, including the need for comprehensive privacy metrics, explainable algorithms, and privacy in social media analytics.

关键词： Privacy enhancing solutions text data Natural language processing Artificial intelligence Machine learning Privacy risk

来源：评论

学校读者我要写书评

暂无评论

text data Augmentation for Deep Learning

引用

JOURNAL OF BIG data 2021年第1期8卷 1-34页

作者： Shorten, Connor Khoshgoftaar, Taghi M. Furht, Borko Florida Atlantic Univ 777 Glades Rd Boca Raton FL 33431 USA

Natural Language Processing (NLP) is one of the most captivating applications of Deep Learning. In this survey, we consider how the data Augmentation training strategy can aid in its development. We begin with the major motifs of data Augmentation summarized into strengthening local decision boundaries, brute force training, causality and counterfactual examples, and the distinction between meaning and form. We follow these motifs with a concrete list of augmentation frameworks that have been developed for text data. Deep Learning generally struggles with the measurement of generalization and characterization of overfitting. We highlight studies that cover how augmentations can construct test sets for generalization. NLP is at an early stage in applying data Augmentation compared to Computer Vision. We highlight the key differences and promising ideas that have yet to be tested in NLP. For the sake of practical implementation, we describe tools that facilitate data Augmentation such as the use of consistency regularization, controllers, and offline and online augmentation pipelines, to preview a few. Finally, we discuss interesting topics around data Augmentation in NLP such as task-specific augmentations, the use of prior knowledge in self-supervised learning versus data Augmentation, intersections with transfer and multi-task learning, and ideas for AI-GAs (AI-Generating Algorithms). We hope this paper inspires further research interest in text data Augmentation.

关键词： data Augmentation Natural Language Processing Overfitting Big data NLP text data

来源：评论

学校读者我要写书评

暂无评论

A network-based CNN model to identify the hidden information in text data

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2022年 590卷

作者： Liu, Yanyan Li, Keping Yan, Dongyang Gu, Shuang Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China

With the development of the internet and big data, the missing or hidden information identification of text data has become an imperative task. At present, the challenge in the hidden information study is judging whether there is hidden information and where it exists. In this paper, hidden information refers to the words that do not appear in a sentence, however, they have certain correlations with the existing words or sentence and have a great influence on the comprehension of a sentence or part of the text data. This paper focuses on discovering the key and influential hidden information in the text data. A keyword-based hidden information extraction framework is proposed in this paper to search hidden entities, with the assumption that the importance of hidden objects is reflected by the keywords in the text data. A network-based Convolution Neural Network (CNN) model is developed to identify the hidden information related to keywords. The model is based on the results of CNN, and cosine similarity is used to judge whether there is hidden information in the source text data or not. We primarily form the word co-occurrence network of text, select the words with the highest degree as keywords, and generate random walk paths on the network. Besides, we use the random walk path where the last word is the keyword to train CNN. In the experimental section, the proposed model is applied to the dataset in 20Newgroups. The results show that the proposed model can effectively identify the hidden information associated with the keywords in the source text data, and the detection accuracy of keywords can reach 98%-99% achieved by CNN. (C) 2021 Elsevier B.V. All rights reserved.

关键词： text data Hidden information detection Network model Random walk CNN

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid deep learning model for taxi demand forecasting based on decomposition of time series and fusion of text data

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2021年第2期41卷 3355-3371页

作者： Zhu, Kun Zhang, Shuai Zhang, Wenyu Zhang, Zhiqiang Zhejiang Univ Finance & Econ Sch Informat Management & Artificial Intelligence Hangzhou 310018 Peoples R China

Accurate taxi demand forecasting is significant to estimate the change of demand to further make informed decisions. Although deep learning methods have been widely applied for taxi demand forecasting, they neglect the complexity of taxi demand data and the impact of event occurrences, making it hard to effectively model the taxi demand in highly dynamic areas (e.g., areas with frequent event occurrences). Therefore, to achieve accurate and stable taxi demand forecasting in highly dynamic areas, a novel hybrid deep learning model is proposed in this study. First, to reduce the complexity of taxi demand time series, the seasonal-trend decomposition procedures based on loess is employed to decompose the time series into three simpler components (i.e., seasonal, trend, and remainder components). Then, different forecasting methods are adopted to handle different components to obtain robust forecasting results. Moreover, considering the instability and nonlinearity of the remainder component, this study proposed to fuse the event features (in particular, text data) to capture the unusual fluctuation patterns of remainder component and solve its extreme value problem. Finally, genetic algorithm is applied to determine the optimal weights for integrating the forecasting results of three components to obtain the final taxi demand. The experimental results demonstrate the better accuracy and reliability of the proposed model compared with other baseline forecasting models.

关键词： Taxi demand forecasting deep learning seasonal-trend decomposition procedures based on loess data fusion text data genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Online Portfolio Selection of Fuzzy Mean Regression Strategy Considering Investor Sentiment Based on text data

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2024年第1期17卷 1-11页

作者： Zeng, Zhiming Xu, Weijun Peng, Zijin Zhong, Yannan South China Univ Technol Sch Business Adm Guangzhou 510641 Guangdong Peoples R China Greater Bay Intelligent Finance & Risk Management Guangzhou 510641 Guangdong Peoples R China Guangzhou Baiyun Int Airport Co Ltd Planning & Dev Dept Guangzhou 510641 Guangdong Peoples R China Guangdong Univ Finance & Econ Sch Econ Guangzhou 510320 Guangdong Peoples R China

Investors are often affected by emotion, cognition, and other psychological factors in stock trading when making decisions. At present, people can use machine learning and other technologies to obtain a massive amount of text data from the Internet to mine information related to investor behavior and sentiment. Building intelligent online portfolio trading strategies that consider investor sentiment has become an important topic and key challenge in the financial field. Therefore, this paper explores how to use text data to depict investor sentiment, fuzzifies historical stock price data, designs a new weight transfer equation, and finally obtains a novel fuzzy mean regression strategy that considers investor sentiment based on text data. We conduct empirical tests on this strategy by using the stock price data selected from CSI300 constituent stocks, as well as the text data of investors' opinions on the internet. The results show that the strategy proposed in this study has a higher Calmar ratio than other mean regression strategies previously studied.

关键词： Online portfolio Fuzzy Mean regression Investor sentiment text data

来源：评论

学校读者我要写书评

暂无评论

A Network Method for Identifying the Root Cause of High-Speed Rail Faults Based on text data

引用

ENERGIES 2019年第10期12卷

作者： Yang, Liu Li, Keping Zhao, Dan Gu, Shuang Yan, Dongyang Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Renmin Univ China Sch Informat Minist Educ Key Lab Data Engn & Knowledge Engn Beijing 100872 Peoples R China

Root cause identification is an important task in providing prompt assistance for diagnosis, security monitoring and guidance for specific routine maintenance measures in the field of railway transportation. However, most of the methods addressing rail faults are based on state detection, which involves structured data. Manual cause identification from railway equipment maintenance and management text records is undoubtedly a time-consuming and laborious task. To quickly obtain the root cause text from unstructured data, this paper proposes an approach for root cause factor identification by using a root cause identification-new word sentence (RCI-NWS) keyword extraction method. The experimental results demonstrate that the extraction of railway fault text data can be performed using the keyword extraction method and the highest values are obtained using RCI-NWS.

关键词： information extraction root cause identification railway fault complex network text data

来源：评论

学校读者我要写书评

暂无评论

An Effective Learning Evaluation Method Based on text data with Real-time Attribution - A Case Study for Mathematical Class with Students of Junior Middle School in China

引用

ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 2023年第3期22卷 1-22页

作者： Liu, Shuai He, Tenghui Li, Jingyi Li, Yating Kumar, Akshi Hunan Normal Univ Coll Informat Sci & Engn Hunan Prov Key Lab Intelligent Comp & Language In Lushan Rd 36 Changsha 410081 Peoples R China Delhi Technol Univ Dept Comp Sci & Engn DL-42Main Bawana Rd New Delhi 110042 India

In today's intelligent age, the vigorous development of education-based information analysis technology has had a profound impact on the education and teaching process. The use of computational linguistics technology to extract teaching data for learning evaluation is an important hot domain in this research field. Therefore, the study of student learning assessment methods based on text data has become a key issue. The text data extracted from the education process has attributes related to time and operational attributes, which are important indicators to measure the effect of student learning effect. However, these attributes are not focused by the traditional educational effect evaluation method, which make the learning effect of students difficult to measure comprehensively and effectively. In response to this problem, this article first uses perception technology to extract learning text data based on time and operational attributes. Secondly, according to the real-time attributes of text data, such as time and operation attributes, a learning evaluation method based on real-time text data is proposed. Finally, this article compares the traditional evaluation method with the proposed method. The results show that using real-time attribute text data is more effective in students' learning measure.

关键词： text data real time educational technology learning effectiveness K-12

来源：评论

学校读者我要写书评

暂无评论

Learning social networks from text data using covariate information

引用

STATISTICAL METHODS AND APPLICATIONS 2021年第5期30卷 1399-1423页

作者： Yang, Xiaoyi Niezink, Nynke M. D. Nugent, Rebecca Carnegie Mellon Univ Dept Stat & Data Sci Pittsburgh PA 15206 USA

Accurately describing the lives of historical figures can be challenging, but unraveling their social structures perhaps is even more so. Historical social network analysis methods can help in this regard and may even illuminate individuals who have been overlooked by historians, but turn out to be influential social connection points. text data, such as biographies, are a useful source of information for learning historical social networks but the identifcation of links based on text data can be challenging. The Local Poisson Graphical Lasso model models social networks by conditional independence structures, and leverages the number of name co-mentions in the text to infer relationships. However, this method does not take into account the abundance of covariate information that is often available in text data. Conditional independence structure like Poisson Graphical Model, which makes use name mention counts in the text can be useful tools to avoid false positive links due to the co-mentions but given historical tendency of frequently used or common names, without additional distinguishing information, we may introduce incorrect connections. In this work, we therefore extend the Local Poisson Graphical Lasso model with a (multiple) penalty structure that incorporates covariates, opening up the opportunity for similar individuals to have a higher probability of being connected. We propose both greedy and Bayesian approaches to estimate the penalty parameters. We present results on data simulated with characteristics of historical networks and show that this type of penalty structure can improve network recovery as measured by precision and recall. We also illustrate the approach on biographical data of individuals who lived in early modern Britain between 1500 and 1575. We will show how these covariates affect the statistical model's performance using simulations, discuss how it helps to better identify links for the people with common names and those who are trad

关键词： Local Poisson Graphical Lasso model Social networks text data L1 penalty factor Bayesian penalty estimation

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：