检索结果-内蒙古大学图书馆

Stream ETL framework for twitter-based sentiment analysis: Leveraging big data technologies

EXPERT SYSTEMS WITH APPLICATIONS 2025年 261卷

作者： Ismail, Azlan Sazali, Faris Haziq Jawaddi, Siti Nuraishah Agos Mutalib, Sofianita Univ Teknol MARA UiTM Coll Comp Informat & Math Sch Comp Sci Shah Alam 40450 Selangor Malaysia Univ Teknol MARA UiTM Inst Big Data Analyt & Artificial Intelligence IBD Kompleks Al Khawarizmi Shah Alam 40450 Selangor Malaysia

Twitter has emerged as a rich source of real-time data, providing valuable insights across various domains such as healthcare and business. Sentiment analysis is crucial in understanding public reactions and sentiments expressed on Twitter, empowering organizations to make informed decisions. However, efficiently analyzing sentiment from social media data, presents a challenge for real-time streaming. Conventional ExtractTransform-Load (ETL) methods, inadequate for this challenge, limit their applicability in processing vast volumes of Twitter data. big data technologies like Kafka, Spark, Hadoop HDFS, Hive, and HBase have become indispensable in addressing this challenge. To address this, we propose a stream ETL framework for Twitter-based sentiment analysis, leveraging Kafka, Spark, Cassandra, HBase, Hive, and HDFS. Our framework enables data stream processing, bias detection and correction, sentiment-based analysis, and visualization of tweets' geospatial distribution. We present a set of use case studies to illustrate the applicability of the proposed framework comprises of sentiment classification, and bias detection and correction capability. We also present a comparative study to demonstrate the performance of data streaming processing, analysis, and visualization that has been implemented using multiple big data technologies under different parameter settings. Experimental results demonstrate the framework scalability and trade-off factors of the data stream processing pipeline in the execution of big data processing tasks.

关键词： Stream processing Twitter ETL Sentiment analysis big data technologies Spark Cassandra

来源：评论

学校读者我要写书评

暂无评论

big data technologies: An empirical investigation on their adoption, benefits and risks for companies

引用

INTERNATIONAL JOURNAL OF INFORMATION MANAGEMENT 2018年第1期38卷 187-195页

作者： Raguseo, Elisabetta Politecn Torino Dept Management & Prod Engn Corso Duca Abruzzi 24 Turin Italy

Companies currently have to deal with profound changes in the way they manage their business, their customers and their business models, since they are overrun by a data-driven revolution in management. This revolution is due to the wide availability of big data and the fast evolution of big data technologies. big data is recognized as one of the most important areas of future technology, and is fast gaining the attention of many industries, since it can provide high value to companies. This article investigates the adoption levels of big data technologies in companies, and the big data sources used by them. This article also points out the most frequently recognized strategic, transactional, transformational and informational benefits and risks related to the usage of big data technologies by companies. In order to achieve these aims, the paper looks at the differences that exist among companies of different sizes, by comparing medium-sized and large companies, and the differences among companies of different industrial sectors. It provides evidence that only in a few cases these differences are significant. This study could serve as a reference for managers who wish to initiate an evaluation cycle on the adoption and usage of big data technologies.

关键词： big data big data technologies Adoption Benefits Risks Size Industrial sector

来源：评论

学校读者我要写书评

暂无评论

big data technologies in Support of Real Time Capturing and Understanding of Electric Vehicle Customers Dynamics 5

Big Data Technologies in Support of Real Time Capturing and ...

引用

5th IEEE International Conference on Software Engineering and Service Science (ICSESS)

作者： Qiu, Robin G. Wang, Katie Li, Shan Dong, Jin Xie, Ming Penn State Univ Div Engn University Pk PA 16802 USA NUAA NUAA IBM Logist & Serv Sci Lab Nanjing Jiangsu Peoples R China IBM China Res Lab Beijing 100094 Peoples R China

ISBN: (纸本)9781479932795

Energy overconsumption and greenhouse gas emission have been contributing to air pollutions and the global warming for years. The unceasingly increasing number of fossil fuels based vehicles around the world is considered as one of main factors making to the situation worse year by year. Electric vehicles (EV) are promoted as a viable and promising alternative transportation means for customers. However, there is an array of issues hindering EVs from the fast adoption in the global auto market. As these issues bear different priorities that surely vary with marketplaces, it becomes essential for EV makers and governments to capture and understand the dynamics of EV consumers in real time. This paper explores how the emerging big data technologies can be applied to facilitate the process of deciphering the acceptance and behavior of EV customers from marketplace to marketplace. A data-collecting web system is discussed. IBM bigInsights platform technologies, including Hadoop, Streams, SPSS modeler and text analytics, are utilized for looking into the insights of collected data. Examples are provided to show the promising future of big data technologies in the field of customer analytics in today's globalized economy.

关键词： Electric vehicles customer behavior customer dyanmics big data technologies InfoSphere bigInsights incentives policies

来源：评论

学校读者我要写书评

暂无评论

A distributed group recommendation system based on extreme gradient boosting and big data technologies

引用

APPLIED INTELLIGENCE 2019年第12期49卷 4128-4149页

作者： Hammou, Badr Ait Lahcen, Ayoub Ait Mouline, Salma Mohammed V Univ Fac Sci Rabat IT Ctr LRITAssociated Unit CNRST URAC 29 Rabat Morocco Ibn Tofail Univ Natl Sch Appl Sci ENSA LGS Kenitra Morocco

Personalized recommendation systems have emerged as useful tools for recommending the appropriate items to individual users. However, in such situations, some items tend to be consumed by groups of users, such as tourist attractions or television programs. With this purpose in mind, Group Recommender Systems (GRSs) are tailored to help groups of users to find suitable items according to their preferences and needs. In general, these systems often confront the sparsity problem, which negatively affects their efficiency. With the increase in the number of users, items, groups, and ratings in the system. data becomes too big to be processed efficiently by traditional systems. Thus, there is an increasing need for distributed recommendation approaches able to manage the issues related to big data and sparsity problem. In this paper, we propose a distributed group recommendation system, which is designed based on Apache Spark to handle large-scale data. It integrates a novel proposed recommendation method, a dimension reduction technique, with supervised and unsupervised learning for dealing efficiently with the curse of dimensionality problem, detecting the groups of users, and improving the prediction quality. Experimental results on three real-world data sets show that our proposal is significantly better than other competitors.

关键词： big data technologies Group recommendation Clustering Machine learning NoSQL database Apache spark

来源：评论

学校读者我要写书评

暂无评论

Enhancing ERP Responsiveness Through big data technologies: An Empirical Investigation

引用

INFORMATION SYSTEMS FRONTIERS 2024年第1期26卷 251-275页

作者： Bandara, Florie Jayawickrama, Uchitha Subasinghage, Maduka Olan, Femi Alamoudi, Hawazen Alharthi, Majed Loughborough Univ Sch Business & Econ Loughborough LE11 3TU England Auckland Univ Technol Fac Business Econ & Law 120 Mayoral Dr Auckland New Zealand Univ Essex Essex Business Sch Southend On Sea SS1 1LW England King Abdulaziz Univ Coll Business Mkt Dept POB 344 Rabigh 21911 Saudi Arabia King Abdulaziz Univ Coll Business Finance Dept POB 344 Rabigh 21911 Saudi Arabia

Organizations are integrating big data technologies with Enterprise Resource Planning (ERP) systems with an aim to enhance ERP responsiveness (i.e., the ability of the ERP systems to react towards the large volumes of data). Yet, organizations are struggling to manage the integration between the ERP systems and big data technologies, leading to lack of ERP responsiveness. For example, it is difficult to manage large volumes of data collected through big data technologies and to identify and transform the collected data by filtering, aggregating and inferencing through the ERP systems. Building on this motivation, this research examined the factors leading to ERP responsiveness with a focus on big data technologies. The conceptual model which was developed through a systematic literature review was tested using Structural equation modelling (SEM) performed on the survey data collected from 110 industry experts. Our results suggested 12 factors (e.g., big data management and data contextualization) and their relationships which impact on ERP responsiveness. An understanding of the factors which impact on ERP responsiveness contributes to the literature on ERP and big data management as well as offers significant practical implications for ERP and big data management practice.

关键词： ERP systems ERP responsiveness big data technologies Systematic literature review Structural equation modelling

来源：评论

学校读者我要写书评

暂无评论

Social customer relationship management: taking advantage of Web 2.0 and big data technologies

引用

SPRINGERPLUS 2016年第1期5卷 1页

作者： Orenga-Rogla, Sergio Chalmeta, Ricardo Unversitat Jaume I Dept Lenguajes & Sistemas Informat Res Grp Integrat & Re Engn Syst IRIS Ave Vicent Sos Baynat S-N Castellon de La Plana Spain

The emergence of Web 2.0 and big data technologies has allowed a new customer relationship strategy based on interactivity and collaboration called Social Customer Relationship Management (Social CRM) to be created. This enhances customer engagement and satisfaction. The implementation of Social CRM is a complex task that involves different organisational, human and technological aspects. However, there is a lack of methodologies to assist companies in these processes. This paper shows a novel methodology that helps companies to implement Social CRM, taking into account different aspects such as social customer strategy, the Social CRM performance measurement system, the Social CRM business processes, or the Social CRM computer system. The methodology was applied to one company in order to validate and refine it.

关键词： Social customer relationship management Customer engagement Web 2.0 technologies big data technologies

来源：评论

学校读者我要写书评

暂无评论

On the use of IoT and big data technologies for Real-time Monitoring and data Processing 8

On the use of IoT and Big Data Technologies for Real-time Mo...

引用

8th International Conference on Emerging Ubiquitous Systems and Pervasive Networks (EUSPN) / 7th International Conference on Current and Future Trends of Information and Communication technologies in Healthcare (ICTH)

作者： Nait Maleka, Y. Kharbouch, A. El Khoukhi, H. Bakhouya, M. De Florio, V. El Ouadghiri, D. Latre, S. Blondia, C. Int Univ Rabat Fac Comp Sci & Logist Technopolis Sala Aljadida Morocco Univ My Ismail Fac Sci Zitoune 11201 Meknes Morocco Univ Antwerp Middelheimlaan 1 B-2020 Antwerp Belgium IMEC Math & Comp Sci Dept Middelheimlaan 1 B-2020 Antwerp Belgium VITO Mol Belgium

Recent advances in pervasive technologies, such as wireless ad hoc networks and wearable sensor devices, allow the connection of everyday things to the Internet, commonly denoted as Internet of Things (IoT). IoT is seen as an enabler to the development of intelligent and context-aware services and applications. These services could dynamically react to the environment changes and users' preferences. The main aim is to make users' life more comfortable according to their locations, current requirements, and ongoing activities. However, handling dynamic and frequent context changes is a difficult task without a real-time event/data acquisition and processing platform. big data and IoT technologies have been recently proposed for timely analysing information (i.e., data, events) streams. In this paper, we propose to combine IoT techniques with big data technologies into a holistic platform for continuous and real-time data monitoring and processing. Preliminary experiments have been conducted and results are reported to show the usefulness of this platform in a real-case scenario. (c) 2017 The Authors. Published by Elsevier B.V.

关键词： Internet of Things big data technologies Complex event processing Real-time monitoring and processing Context-awarness

来源：评论

学校读者我要写书评

暂无评论

Service-Oriented Distributed Energy data Management Using big data technologies

Service-Oriented Distributed Energy Data Management Using Bi...

引用

International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)

作者： Gibadullin, R. F. Baimukhametova, G. A. Perukhin, M. Yu KNRTU KAI Dept Comp Syst Kazan Russia KNRTU Dept Automated Syst Collecting & Proc Informat Kazan Russia

ISBN: (纸本)9781538681190

Nowadays, the smart grid becomes a new electrical grid system instead of the traditional grid. It can provide the efficiency and reliability of energy resources. A smart meter possesses the sen-sors which collect information about energy consumption and production at a defined time. A vast amount of data needs to be aggregated, stored and transformed in near real-time for intelli-gent response and decision support in the smart grid. There are many technologies, which can provide the storing, aggregation and processing of the data. Each technology is more suitable for specific tasks. The devices generate a massive amount of data. Therefore, all this data belong to the big data area. Grid man-agement includes the prediction of load and consumer usage behaviours. In order to effectively analyze and storage, this data should use the big data technologies. It can provide fast meth-ods of transmitting. In this article the authors considered the architecture of the smart grid and evaluated this system in the real region.

关键词： Smart grid architecture big data technologies

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Software Parallelism in big data technologies for data-Intensive Architectures 15th

An Analysis of Software Parallelism in Big Data Technologies...

引用

15th European Conference on Software Architecture (ECSA)

作者： Cerezo, Felipe Cuesta, Carlos E. Vela, Belen Univ Rey Juan Carlos VorTIC3 Res Grp C Tulipan S-N Madrid 28933 Spain

ISBN: (纸本)9783030860448;9783030860431

data-intensive architectures handle an enormous amount of information, which require the use of big data technologies. These tools include the parallelization mechanisms employed to speed up data processing. However, the increasing volume of these data has an impact on this parallelism and on resource usage. The strategy traditionally employed to increase the processing power has usually been that of adding more resources in order to exploit the parallelism;this strategy is, however, not always feasible in real projects, principally owing to the cost implied. The intention of this paper is, therefore, to analyze how this parallelism can be exploited from a software perspective, focusing specifically on whether big data tools behave as ideally expected: a linear increase in performance with respect to the degree of parallelism and the data load rate. An analysis is consequently carried out of, on the one hand, the impact of the internal data partitioning mechanisms of big data tools and, on the other, the impact on the performance of an increasing data load, while keeping the hardware resources constant. We have, therefore, conducted an experiment with two consolidated big data tools, Kafka and Elasticsearch. Our goal is to analyze the performance obtained when varying the degree of parallelism and the data load rate without ever reaching the limit of hardware resources available. The results of these experiments lead us to conclude that the performance obtained is far from being the ideal speedup, but that software parallelism still has a significant impact.

关键词： data-intensive architecture Software parallelism Partitioning big data technologies Linear scalability

来源：评论

学校读者我要写书评

暂无评论

Industrial track: Architecting railway KPIs data processing with big data technologies

Industrial track: Architecting railway KPIs data processing ...

引用

IEEE International Conference on big data (big data)

作者： Suleykin, Alexander Panfilov, Peter Bakhtadze, Natalya Russian Acad Sci VA Trapeznikov Inst Control Sci Moscow Russia Natl Res Univ Higher Sch Econ Sch Business Informat Moscow Russia Bauman Moscow State Tech Univ Moscow Russia

ISBN: (纸本)9781728108582

in our conducted research we have built the data processing pipeline for storing railway KPIs data based on big data open-source technologies - Apache Hadoop, Kafka, Karim HDFS Connector. Spark, Airflow and PostgreSQL. Created methodology for data load testing allowed to iteratively perform data load tests with increased data size and evaluate needed cluster software and hardware resources and, finally, detected bottlenecks of solution. As a result of the research we proposed architecture for data processing and storage, gave recommendations on data pipeline optimization. In addition, we calculated approximate cluster machines sizing for current dataset volume for data processing and storage services.

关键词： big data technologies distributed data processing Hadoop Spark railway KPIs

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：