Big Text Data Research Articles

A Novel Statistic-Based Corpus Machine Processing Approach to Refine a Big Textual Data: An ESP Case of COVID-19 News Reports

With developments of modern and advanced information and communication technologies (ICTs), Industry 4.0 has launched big data analysis, natural language processing (NLP), and artificial intelligence (AI). Corpus analysis is also a part of big data analysis. For many cases of statistic-based corpus techniques adopted to analyze English for specific purposes (ESP), researchers extracted critical information by retrieving domain-oriented lexical units. However, even if corpus software embraces algorithms such as log-likelihood tests, log ratios, BIC scores, etc., the machine still cannot understand linguistic meanings. In many ESP cases, function words reduce the efficiency of corpus analysis. However, many studies still use manual approaches to eliminate function words. Manual annotation is inefficient and time-wasting, and can easily cause information distortion. To enhance the efficiency of big textual data analysis, this paper proposes a novel statistic-based corpus machine processing approach to refine big textual data. Furthermore, this paper uses COVID-19 news reports as a simulation example of big textual data and applies it to verify the efficacy of the machine optimizing process. The refined resulting data shows that the proposed approach is able to rapidly remove function and meaningless words by machine processing and provide decision-makers with domain-specific corpus data for further purposes.

A Big-Data–Based Analysis on the Impact of Cruise Tourism Image on Chinese Tourist Satisfaction and Behavioral Intentions

Wu, L.; Dong, C., and Xiong, G., 2020. A big-data–based analysis on the impact of cruise tourism image on Chinese tourist satisfaction and behavioral intentions. In: Gong, D.; Zhang, M., and Liu, R. (eds.), Advances in Coastal Research: Engineering, Industry, Economy, and Sustainable Development. Journal of Coastal Research, Special Issue No. 106, pp. 314–318. Coconut Creek (Florida), ISSN 0749-0208.This research, targeted at Chinese cruise tourists, divides the cruise tourism image into five dimensions: cruise infrastructure, services, leisure and entertainment, cruise brand, and atmosphere. The purpose is to explore the impact of cruise image on Chinese tourists' satisfaction and behavior intention. In this research, all comments on popular cruises “Royal Caribbean International-Spectrum of the Seas,” “Princess-Sapphire Princess,” “Costa-Venezia,” and “Star Cruises-Explorer Dream” on popular China-Japan lanes posted by Chinese cruise tourists on Ctrip in 2019 are extracted with Python software. Word frequency analysis, semantic network analysis, and sentiment analysis in big data text analysis are applied. The results indicate that the image of infrastructure, service image, leisure & entertainment image, cruise brand image and the image of tourism atmosphere of cruises have a significant positive impact on the satisfaction and behavioral intentions of Chinese tourists. In this regard, the recommendations for cruise brands are as follows: (1) To update entertainment items on cruises and improve the maintenance of infrastructure from time to time. (2) To make on-shore activities more interesting. (3) To strengthen the uniqueness of cruise brands. (4) To expand the target customer group. (5) To provide more customized services.

Examining the potential of textual big data analytics for public policy decision-making: A case study with driverless cars in Denmark

The simultaneous growth of textual data and the advancements within Text Analytics enables organisations to exploit this kind of unstructured data, and tap into previously hidden knowledge. However, the utilisation of this valuable resource is still insufficiently unveiled in terms of transport policy decision-making. This research aims to further examine the potential of textual big data analytics in transportation through a real-life case study. The case study, framed together with the Danish Road Directorate or Vejdirektoratet, was designed to assess public opinion towards the adoption of driverless cars in Denmark. Traditionally, the opinion of the public has often been captured by means of surveys for the problem owner. Our study provides demonstrations in which opinion towards the adoption of driverless cars is examined through the analysis of newspaper articles and tweets using topic modelling, document classification, and sentiment analysis. In this way, the research attends to the collective as well as individualised characteristics of public opinion. The analyses establish that Text Analytics may be used as a complement to surveys, in order to extract additional knowledge which may not be captured through the use of surveys. In this regard, the Danish Road Directorate could find the usefulness while understanding the barriers in the results generated from our study, for supplementing their future data collection strategies. However there are also some methodological limitations that need to be addressed before a broader adoption of textual big data analytics for transport policy decision-making may take place.

An unstructured big data approach for country logistics performance assessment in global supply chains

PurposeThe purpose of this study is to explore the potential for the development of a country logistics performance assessment approach based upon textual big data analytics.Design/methodology/approachThe study employs design science principles. Data were collected using the Global Perspectives text corpus that describes the logistics systems of 20 countries from 2006–2014. The extracted texts were processed and analysed using text analytic techniques, and domain experts were employed for training and developing the approach.FindingsThe developed approach is able to generate results in the form of logistics performance assessments. It contributes towards the development of more informed weights of the different country logistics performance categories. That said, a larger text corpus and iterative classifier training is required to produce a more robust approach for benchmarking and ranking.Practical implicationsWhen successfully developed and implemented, the developed approach can be used by managers and government bodies, such as the World Bank and its stakeholders, to complement the Logistics Performance Index (LPI).Originality/valueA new and unconventional approach for logistics system performance assessment is explored. A new potential for textual big data analytic applications in supply chain management is demonstrated. A contribution to performance management in operations and supply chain management is made by demonstrating how domain-specific text corpora can be transformed into an important source of performance information.

Competitor intelligence and analysis (CIA) model and online reviews: integrating big data text mining with network analysis for strategic analysis

Purpose This study aims to propose a competitor intelligence and analysis (CIA) model that can be used for the analysis of a firm’s competitors. Empirically, it investigates the application of the CIA model on online reviews. This proposed model clarifies the confusion between terms such as competitive intelligence, competitor intelligence and competitor analysis and provides a more efficient process for managers. Design/methodology/approach The approach of the model integrates text mining techniques as a big data method with network analysis to form a competitor analysis. This study has considered two centrality metrics – degree centrality and betweenness centrality – to identify the functional associations among the resources elaborated by the customers of the hotels. Findings Findings show online reviews may be used as a solid source of intelligence. The intelligence maps visualized through the text-net technique is an efficient representation of tourist satisfaction and dissatisfaction with a tourism company and its competitors. Practical implications The proposed approach can be used in the hotel industry along with many others. The implications for scholars and managers and the possible directions for future research are also discussed in the study. Originality/value This study develops a new approach for competitive intelligence practices in the hotel industry and tests a new method for competitor analysis as a part of the competitive intelligence and analysis approach developed in this study.

Big data and sentiment analysis: A comprehensive and systematic literature review

SummarySentiment analysis can extract information from many text sources such as reviews, news, and blogs; then it classifies them based on their polarity. Moreover, big data is produced via mobile networks and social media. Applications of sentiment analysis on big data are used as a way of classifying the opinions into diverse sentiment. Accordingly, performing sentiment analysis on big data can be helpful for a business to take useful commercial insights from text‐oriented content. However, there are very few comprehensive investigations and profound argument in this context. The goal of this paper is to provide a comprehensive and systematic investigation of the state‐of‐the‐art techniques and highlight the directions for future research. In this paper, we used systematic literature review method and in the first step, we obtained 15 351 articles; then, based on different filters, 48 related articles were attained. We have selected 23 articles based on the year of publication, the relevance of the journal, the completeness of the text, the nonrepeatability of the title, and the page number. Also, we have categorized big data and sentiment analysis into two classifications: centralized and distributed platforms. Furthermore, the disadvantages and advantages of the investigated techniques are studied and their key issues are emphasized. Consequently, this study shows that a better analysis of textual big data in terms of sentiment increases efficiency, flexibility, and intelligence. By providing comparative information and analyzing the current developments in this area, this paper will directly support academics and practicing professionals for better handling of big data in the field of sentiment analysis. This study sheds some new light on using sentiment analysis and big data for public opinion estimation and prediction.

From the Editors: Introduction to the Emerging Discourse Incubator on the Topic of Emerging Approaches for Developing Supply Chain Management Theory

The Journal of Supply Chain Management’s 2020 Emerging Discourse Incubator hopes to stimulate the development of supply chain specific theory. Well‐executed case‐based research will always be an appropriate means for developing supply chain theory. However, this EDI seeks to highlight emerging approaches to theory building that provide alternatives to case‐based research or can be used as a source of triangulation with it. To start that discourse, this issue offers three emergent approaches. In “Theorizing Supply Chains with Qualitative Big Data and Topic Modeling,” Tima Bansal, Jury Gualandris, and Nahyun Kim explore the application of topic modeling to develop supply chain theory from qualitative textual big data evidence. Anne Touboulic, Lucy McCarthy, and Lee Matthews illustrate the use of critical engaged research to develop supply chain theory in “Re‐Imagining Supply Chain Challenges Through Critical Engaged Research.” In “A New Methodology for Supply Chain Management: Discourse Analysis and its Potential for Theoretical Advancement,” Cynthia Hardy, Vikram Bhakoo, and Steve Maguire describe the potential for discourse analysis for developing supply chain management theory. These are but a few examples of potential approaches to developing supply chain theory. We welcome submissions on additional approaches and sources of data that are used in other disciplines, but have yet to be applied in the context of developing supply chain theory, and submissions on approaches that are emergent in the social sciences, in general. JSCM welcomes submissions for this EDI through the end of 2020.

Text Big Data Analysis on Environmental Problems and Civil Education focused on Water Quality and Algae

시민교육에 대한 정의가 광범위하지만 일반인들에게 기초교육의 기회를 제공하고 글로벌 시민으로서의 덕목을 함양한다는 점에서 환경문제와의 관련이 매우 크다. UN에서 규정한 것처럼 지속가능한 사회로의 발전을 위한 환경교육은 시민교육 측면에서 중요하다 할 수 있다. 본 연구는 2000년부터 2013년까지 동아일보 코퍼스를 분석하여 환경과 관련된 대상어인 녹조를 선정하고 이와 관련된 공기어에 대한 네트워크 분석을 수행하여 녹조에 대한인식 변화를 추적하였다. 또한 최근의 트렌드 분석을 위해 2019년 12월부터 2020년 1월까지의 텍스트 빅데이터에 대해 감성분석과 연관어 분석을 실시하여 녹조에 대한 최근 인식을 도출하였다. 추가적으로 시계열 수질자료를 실제 오염부하에 대해 분석하여 Granger-인과관계 검증을 통해서 계층 간의 인식차이를 도출하였다. 결론적으로 현재 녹조에 대한 인식은 미디어의 영향이 매우 크게 작용한 것으로 판단되며, 과거 인테넷 등과 같이 정보 접근성이 떨어질 때와 비교하면 환경문제에 있어서의 시민교육은 차별화되고 타겟화된 접근전략과 이행계획이 필요하다고 할 수 있다. 여성과 남성이 연령에 따라 녹조문제에 대해 다른 인식 양상을 보이는 것은 정치적인 입장차이도 존재하는 것으로 분석되었다.Although the definition of civil education is broad, it is very relevant to environmental issues in providing the opportunities to the public as needs of basic education and virtues of global citizenship. This study investigated the change of perception of harmful algae blooms (HABs) by analyzing the Dong-A newspaper corpus from 2000 to 2013 to extract co-occurring words and conducting text big data analysis from December 2019 to January 2020 to derive the recent trends of HABs. In addition, we conducted the Granger-causality test for text minded HABs and co-occurring words. Prior to the analysis, we also introduced time-series analysis on actual water quality data and compared with perception trends. In conclusion, the current perception of HABs seems to have a significant influence on the media and social network service. In this regard, civil education requires differentiated and targeted approaches and implementation plans. It is analyzed that there is a political position difference between femal and male groups in terms of HABs accordingly.

Applying Big Data visualization to detect trends in 30 years of performance reports

Evaluators worldwide are dealing with a growing amount of unstructured electronic data, predominantly in textual format. Currently, evaluators analyze textual Big Data primarily using traditional content analysis methods based on keyword search, a practice that is limited to iterating over predefined concepts. But what if evaluators cannot define the necessary keywords for their analysis? Often we should examine trends in the way certain organizations have been operating, while our raw data are gigabytes of documents generated by that organization over decades. The problem is that in many cases we do not know what exactly we need to look for. In such cases, traditional analytical machinery would not provide an adequate solution within reasonable time—instead, heavy-lifting Big Data Science should be applied. We propose an automated, quantitative, user-friendly methodology based on text mining, machine learning, and data visualization, which assists researchers and evaluation practitioners to reveal trends, trajectories, and interrelations between bits and pieces of textual information in order to support evaluation. Our system automatically extracts a large amount of descriptive terminology for a particular domain in a given language, finds semantic connections between documents based on the extracted terminology, visualizes the entire document repository as a graph of semantic connections, and leads the user to the areas on that graph where most interesting trends can be observed. This article exemplifies the new method on 1700 performance reports, showing that the method can be used successfully, supplying evaluators with highly important information which cannot be revealed using other methods. Such exploratory exercise is vital as a preliminary exploratory phase for evaluations involving unstructured Big Data, after which a range of evaluation methods can be applied. We argue that our system can be successfully implemented on any domain evaluated.

Teaching Natural Language Processing through Big Data Text Summarization with Problem-Based Learning

Natural language processing (NLP) covers a large number of topics and tasks related to data and information management, leading to a complex and challenging teaching process. Meanwhile, problem-based learning is a teaching technique specifically designed to motivate students to learn efficiently, work collaboratively, and communicate effectively. With this aim, we developed a problem-based learning course for both undergraduate and graduate students to teach NLP. We provided student teams with big data sets, basic guidelines, cloud computing resources, and other aids to help different teams in summarizing two types of big collections: Web pages related to events, and electronic theses and dissertations (ETDs). Student teams then deployed different libraries, tools, methods, and algorithms to solve the task of big data text summarization. Summarization is an ideal problem to address learning NLP since it involves all levels of linguistics, as well as many of the tools and techniques used by NLP practitioners. The evaluation results showed that all teams generated coherent and readable summaries. Many summaries were of high quality and accurately described their corresponding events or ETD chapters, and the teams produced them along with NLP pipelines in a single semester. Further, both undergraduate and graduate students gave statistically significant positive feedback, relative to other courses in the Department of Computer Science. Accordingly, we encourage educators in the data and information management field to use our approach or similar methods in their teaching and hope that other researchers will also use our data sets and synergistic solutions to approach the new and challenging tasks we addressed.

Multi-keywords carrier-free text steganography method based on Chinese Pinyin

By combining big data with the characteristics of steganography, carrier-free steganography was proposed to resist all the steganalysis attacks. A novel method named multi-keywords carrier-free text steganography method based on Chinese Pinyin is introduced in this paper. In the proposed method, the hidden tags are selected from the Pinyin combinations of two words. In the process of information hiding, the part of speech (POS) is used for hiding the number of keywords. Also, the redundancy of hidden tags in extraction process is eliminated by ensuring the uniqueness of each hidden tag in each stego-text. Meanwhile, the way of joint retrieval is used for hiding multi-keywords. Experimental results show that the proposed method has good performance in the hiding capacity, the success rate of hiding, the extraction accuracy and the time efficiency with appropriate hidden tags and large-scale of the big text data.

Multi-keywords carrier-free text steganography method based on Chinese Pinyin

By combining big data with the characteristics of steganography, carrier-free steganography was proposed to resist all the steganalysis attacks. A novel method named multi-keywords carrier-free text steganography method based on Chinese Pinyin is introduced in this paper. In the proposed method, the hidden tags are selected from the Pinyin combinations of two words. In the process of information hiding, the part of speech (POS) is used for hiding the number of keywords. Also, the redundancy of hidden tags in extraction process is eliminated by ensuring the uniqueness of each hidden tag in each stego-text. Meanwhile, the way of joint retrieval is used for hiding multi-keywords. Experimental results show that the proposed method has good performance in the hiding capacity, the success rate of hiding, the extraction accuracy and the time efficiency with appropriate hidden tags and large-scale of the big text data.

The Construction Site Management of Concrete Prefabricated Buildings by ISM-ANP Network Structure Model and BIM under Big Data Text Mining

The Construction Site Management of Concrete Prefabricated Buildings by ISM-ANP Network Structure Model and BIM under Big Data Text Mining

Visualization of Big Data Text Analytics in Financial Industry: A Case Study of Topic Extraction for Italian Banks

Textual data and analysis can derive new insights and bring valuable business insights. These insights can be further leveraged by making better future business decisions. Sources that are used for text analysis in financial industry vary from internal word documents, email to external sources like social media, websites or open data. The system described in this paper will utilize data from social media (Twitter) and tweets related to Italian banks, in Italian. This system is based on open source tools (R language) and topic extraction model was created to gather valuable information. This paper describes methods used for data ingestion, modelling, visualizations of results and insights.

Techniques of Big Data Text Summarization

In the web industry 4.0, big data are playing a key role in the organizations of their digital transformation journey. Data has also changed intensely in recent years, in volume, variety and velocity. Its fast development attributed to the extensive digitization of business progressions globally. In simple term, data has turn into the new currency of business and its further quick growth will be key transformation and growth of organizations globally. Vast amount of online information, available in healthcare, social media websites, e-commerce web pages, e-books, legal domain, e-news, etc. has made text processing a vital extent of research. The paper starts with introduction about the evolution of web industry 4.0 and digitalization. Followed by the introduction, the paper discusses about big data and text summarization techniques. Further, it describes the literature of text mining that have taken in the recent years. The main objective of this paper is to discuss about the big data text summarization issues and challenges. The paper starts with general introduction of big data and text mining and text summarization. Further it describes recent advances in big data text summarization, and then delve into extraction and abstraction-based text summarization. Finally, the paper concludes with some future research directions.

A new corpus-based convolutional neural network for big data text analytics

Companies market their services and products on social media platforms with today's easy access to the internet. As result, they receive feedback and reviews from their users directly on their social media sites. Reading every text is time-consuming and resourcedemanding. With access to technology-based solutions, analyzing the sentiment of all these texts gives companies an overview of how positive or negative users are on specific subjects will minimize losses. In this paper, we propose a deep learning approach to perform sentiment analysis on reviews using a convolutional neural network model, because that they have proven remarkable results for text classification. We validate our convolutional neural network model using large-scale data sets: IMDB movie reviews and Reuters data sets with a final accuracy score of ~86% for both data sets.

A deeper look at the collective intelligence phenomenon

For the upcoming conference on Intelligence Studies at ICI 2020 in Bad Nauheim, Germany the focus of this issue of JISIB is on collective intelligence and foresight. The first two papers by Søilen and Almedia and Lesca deal with collective intelligence from an intelligence studies perspective. It may be said that the Internet itself is a gigantic collective intelligence effort, the largest in human history. Open source is a prerequisite for this system to work for everyone. The article by Černý et al. is on open source. All other contributions are on the connection between the Internet, software and intelligence. This issue consists of seven articles to compensate for two articles that were taken out by editors in the last issue. The first article by Søilen entitled “Making sense of the collective intelligence field: a review” is a historical review of the field of collective intelligence. The paper shows how collective intelligence is an interdisciplinary field and argues there is a flaw in the notion of “wisdom of crowds”. Collective intelligence can be understood in terms of social systems theory and as such this approach has been fruitful for the social sciences, although so far not very popular. It also bares relevance for the study of business and economics. The second article by Almeida and Lesca is entitled “Collective intelligence process to interpret weak signals and early warnings”. Early warning and the detection of weak signals is a vital topic for any intelligence organization. Two aspects are discussed in the paper, the importance of new technology and collective sense making or interpretation The third article by Shaikh and Singhal entitled “Study on the various intellectual property management strategies used and implemented by ICT firms for business intelligence” deals with intellectual property rights and patenting strategies. The authors identify a number of defensive and offensive IP strategies applied to ICT companies. The results have a bearing on patent acquisitions. The fourth article by Lamrhari et al. is entitled “Web intelligence for understanding customer satisfaction: application of Latent Dirichlet Allocation (LDA) and the Kano model”. Customer satisfaction today is mostly measured with data from the internet, using different business intelligence techniques. The Kano model is still valuablei,ii, but the way we gather information to assess the different levels in the model has changed. The authors use Latent Dirichlet Allocation to analyze the voice of customer (VOC) in online reviews. They suggest that BI techniques and a fuzzy-Kano model can enable companies to better understand their customers’ online reviews. The fifth article by Nahili et al. is entitled “A new corpus-based convolutional neutral network for big data text analysis”. Companies need efficient ways to analyze everything that is said about them on the internet (reviews, comments). The paper suggests a convolutional neural network (CNN) as it has been successfully used for text classification. IMDB movie reviews and Reuters datasets were used for the experiment. The sixth article by Černý et al. is entitled “Using open data and google search data for competitive intelligence analysis”. Taking the Czech antidepressant market as an example, the authors show how competitive intelligence can be obtained using Google Search data, Google Trend and other OSINT sources. The seventh article by Dadkhah et al. is entitled “The potential of business intelligence tools for expert findings”. The paper suggests a way for researchers to find experts using business intelligence tools. The same method may also be used by any business or person looking for experts on a specific topic. As always, we would above all like to thank the authors for their contributions to this issue of JISIB. Thanks to Dr. Allison Perrigo for reviewing English grammar and helping with layout design for all articles and to the Swedish Research Council for continuous financial support. We hope to see you all at the ICI 2020 on the 16-17 March, 2020. The deadline for the two-page abstract submission is March 1st, 2020.

An Efficient and Unique TF/IDF Algorithmic Model-Based Data Analysis for Handling Applications with Big Data Streaming

As the field of data science grows, document analytics has become a more challenging task for rough classification, response analysis, and text summarization. These tasks are used for the analysis of text data from various intelligent sensing systems. The conventional approach for data analytics and text processing is not useful for big data coming from intelligent systems. This work proposes a novel TF/IDF algorithm with the temporal Louvain approach to solve the above problem. Such an approach is supposed to help the categorization of documents into hierarchical structures showing the relationship between variables, which is a boon to analysts making essential decisions. This paper used public corpora, such as Reuters-21578 and 20 Newsgroups for massive-data analytic experimentation. The result shows the efficacy of the proposed algorithm in terms of accuracy and execution time across six datasets. The proposed approach is validated to bring value to big text data analysis. Big data handling with map-reduce has led to tremendous growth and support for tasks like categorization, sentiment analysis, and higher-quality accuracy from the input data. Outperforming the state-of-the-art approach in terms of accuracy and execution time for six datasets ensures proper validation.

Maximum Frequent Item Set based Clustering Algorithm for Big Text Data

Due to fast growth of internet and continuous expansion of World Wide Web like digital libraries, online news contributes to massive amount of electronic unstructured text documents on the web. Although lot traditional techniques are available to extract the knowledge from large collection of text documents, still to improve precision of the web search retrieval and to find most appropriate documents from huge text collections proficiently is a big challenge. Clustering techniques helps the search engine to retrieve the documents. The proposed system overcomes existing problems using bivariate n-gram frequent item clustering algorithm by concept of maximum frequent set which maintain the sequence and meaning of sentence in order to reduce huge dimension and and frequent item sets finds similarity. Then based on maximum document occurrence we cluster the documents. Thus our method obtains quality of clusters when compared with existing methodologies and improves the efficiency. The experiment is shown for sample Newsgroup dataset for existing K-Mean and FICMDO (Frequent item clustering method based on maximum document occurrence) and proved the f-measure is higher for our algorithm. Since the f-measure increases, obtains efficient clusters. Hence it is faster and efficient big data method which improves the performance when compared with vector space model like K-Means algorithm.

Forecasting election results by studying brand importance in online news

This study uses the semantic brand score, a novel measure of brand importance in big textual data, to forecast elections based on online news. About 35,000 online news articles were transformed into networks of co-occurring words and analyzed by combining methods and tools from social network analysis and text mining. Forecasts made for four voting events in Italy provided consistent results across different voting systems: a general election, a referendum, and a municipal election in two rounds. This work contributes to the research on electoral forecasting by focusing on predictions based on online big data; it offers new perspectives regarding the textual analysis of online news through a methodology which is relatively fast and easy to apply. This study also suggests the existence of a link between the brand importance of political candidates and parties and electoral results.