Investigating German Higher Education Institutions' Transfer Activities: New Measurements Based on Web Mining

2023 | International Conference on Information Systems | Citations: 0

Authors: Schmitt, Michelle; Schröder, Christian; Beck, Günter W.; Werner, Arndt

Abstract: In recent years, higher education institutions (HEI) have expanded their involv ... Expand

Abstract: In recent years, higher education institutions (HEI) have expanded their involvement in diverse transfer activities (TA), extending beyond traditional teaching and research roles. These TA are often heterogeneous and informal, which makes measuring their full scope and effects challenging. In this article, we propose a new and straightforward to implement approach for mastering this task. In a first step, we theoretically derive three different dimensions of transfer, namely the transfer of knowledge, technology and personnel. For each of these categories, we develop an artificial intelligence (AI) optimized keyword list. Finally, we use these lists and apply web mining techniques and natural language processing (NLP) to measure TA from German HEI. To this end, we analyze a total of 299,229 texts from 376 German HEI websites. Our study shows that our proposed approach represents an effective and valuable tool for measuring TA from HEI and provides a foundation for further research. Collapse

Topics: website knowledge sharing artificial intelligence entrepreneurship open source

Methods: web mining natural language processing computational algorithm descriptive statistic literature study

Determining Link Relevancy in Tweets Related to Multiple Myeloma Using Natural Language Processing

2022 | HICSS | Citations: 0

Authors: Van Hoven, Sean; Thoms, Brian; Botts, Nathan

Abstract: Social media platforms continue to play a leading role in the evolution of how p ... Expand

Abstract: Social media platforms continue to play a leading role in the evolution of how people share and consume information. Information is no longer limited to updates from a user’s immediate social network but have expanded to an abstract network of feeds from across the global internet. Within the health domain, users rely on social media as a means for researching symptoms of illnesses and the myriad of therapies posted by others with similar implications. Whereas in the past, a single user may have received information from a limited number of local sources, now a user can subscribe to information feeds from around the globe and receive real-time updates on information important to their health. Yet how do users know that the information they are receiving is relevant or not? In this age of fake news and widespread disinformation the global domain of medical knowledge can be tough to navigate. Both legitimate and illegitimate practitioners leverage social media to spread information outside of their immediate network in order to reach, sway, and enlist a larger audience. In this research, we develop a system for determining the relevancy of linked webpages using a combination of web mining through Twitter hashtags and natural language processing (NLP). Collapse

Topics: Twitter web page website application programming interface Python

Methods: computational algorithm natural language processing Cross-Industry Standard Process for Data Mining web mining data modeling

Big data analytics in health sector: Theoretical framework, techniques and prospects

2020 | International Journal of Information Management | Citations: 5

Authors: Galetsi, Panagiota; Katsaliaki, Korina; Kumar, Sameer

Abstract: Clinicians, healthcare providers-suppliers, policy makers and patients are exper ... Expand

Abstract: Clinicians, healthcare providers-suppliers, policy makers and patients are experiencing exciting opportunities in light of new information deriving from the analysis of big data sets, a capability that has emerged in the last decades. Due to the rapid increase of publications in the healthcare industry, we have conducted a structured review regarding healthcare big data analytics. With reference to the resource-based view theory we focus on how big data resources are utilised to create organization values/capabilities, and through content analysis of the selected publications we discuss: the classification of big data types related to healthcare, the associate analysis techniques, the created value for stakeholders, the platforms and tools for handling big health data and future aspects in the field. We present a number of pragmatic examples to show how the advances in healthcare were made possible. We believe that the findings of this review are stimulating and provide valuable information to practitioners, policy makers and researchers while presenting them with certain paths for future research. Collapse

Topics: big data healthcare data database system Apache Hadoop MapReduce

Methods: literature sample machine learning qualitative content analysis literature study synthesis

Theories: resource based view of the firm

Semantic and Sentiment Dissonant Framing Effects on Online News Sharing

2020 | Communications of the Association for Information Systems | Citations: 1

Authors: Yim, Dobin; Gao, Qiang; Khuntia, Jiban

Abstract: Information artifacts incorporate cognitive elements in their design to inform u ... Expand

Abstract: Information artifacts incorporate cognitive elements in their design to inform users about and entice them to consume relevant content. Sparse research has examined how to design cognitive elements in information artifacts in the digital news platforms context. This study investigates how information artifacts’ semantic and sentiment elements convey meaning and emotion to elicit users to share online news. We propose a dissonant framework and hypothesize that three dissonance dimensions (namely, semantic dissonance, textual sentiment dissonance, and visual sentiment dissonance) influence news sharing. We tested the hypotheses using real-world data from 2013 to 2015 from Mashable—a popular digital news platform. We used novel machine-learning techniques to extract topics and sentiments from text and photos in news articles. Findings from our econometric analysis support that textual sentiment and visual sentiment dissonance positively affect news sharing. Collapse

Topics: digital news social media Google+ usability decision making

Methods: statistical hypothesis test sentiment analysis term frequency–inverse document frequency natural language processing design artifact

Theories: elaboration likelihood model cognitive dissonance theory

Business intelligence in online customer textual reviews: Understanding consumer perceptions and influential factors

2017 | International Journal of Information Management | Citations: 30

Authors: Xu, Xun; Wang, Xuequn; Li, Yibai; Haghighi, Mohammad

Abstract: With the rapid development of information technology, customers not only shop on ... Expand

Abstract: With the rapid development of information technology, customers not only shop online—they also post reviews on social media. This user-generated content (UGC) can be useful to understand customers’ shopping experiences and influence future customers’ purchase intentions. Therefore, business intelligence and analytics are increasingly being advocated as a way to analyze customers’ UGC in social media and support firms’ marketing activities. However, because of its open structure, UGC such as customer reviews can be difficult to analyze, and firms find it challenging to harness UGC. To fill this gap, this study aims to examine customer satisfaction and dissatisfaction toward attributes of hotel products and services based on online customer textual reviews. Using a text mining approach, latent semantic analysis (LSA), we identify the key attributes driving customer satisfaction and dissatisfaction toward hotel products and service attributes. Additionally, using a regression approach, we examine the effects of travel purposes, hotel types, star level, and editor recommendations on customers’ perceptions of attributes of hotel products and services. This study bridges customer online textual reviews with customers’ perceptions to help business managers better understand customers’ needs through UGC. Collapse

Topics: customer satisfaction online review analytical information system website database system

Methods: natural language processing survey regression analysis method computational algorithm term frequency–inverse document frequency

Theories: expectation disconfirmation theory

Integrating expert knowledge and multilingual web crawling data in a lead qualification system

2016 | Decision Support Systems | Citations: 0

Authors: D’Haen, J.; Van den Poel, D.; Thorleuchter, D.; Benoit, D. F.

Abstract: Qualifying prospects as leads to contact is a complex exercise. Sales representa ... Expand

Abstract: Qualifying prospects as leads to contact is a complex exercise. Sales representatives often do not have the time or resources to rationally select the best leads to call. As a result, they rely on gut feeling and arbitrary rules to qualify leads. Model-based decision support systems make this process less subjective. Standard input for such an automated lead qualification system is commercial data. Commercial data, however, tends to be expensive and of ambiguous quality due to missing information. This study proposes web crawling data in combination with expert knowledge as an alternative. Web crawling data is freely available and of higher quality as it is generated by companies themselves. Potential customers use websites as a main information source, so companies benefit from correct and complete websites. Expert knowledge, on the other hand, augments web crawling data by inserting specific information. Web data consists of text that is converted to numbers using text mining techniques that make an abstraction of the text. A field experiment was conducted to test how a decision support system based on web crawling data and expert knowledge compares to a basic decision support system within an international energy retailer. Results verify the added value of the proposed approach. Collapse

Topics: website web crawling decision support system business-to-business database system

Methods: machine learning computational algorithm cluster analysis natural language processing experiment

Extending Web Mining to Digital Forensics Text Mining

2016 | Americas Conference on Information Systems | Citations: 0

Authors: Hicks, Chelsea; Beebe, Nicole; Haliscak, Brandi

Abstract: As digital devices become increasingly integral to our daily lives, so too is th ... Expand

Abstract: As digital devices become increasingly integral to our daily lives, so too is the prevalence of digital evidence in the form of unstructured, textual data. Such data exists in both cyber and non-cyber crime cases. As a result, text mining is an important forensic technique to digital forensic investigators. However, text mining in the digital forensics domain is a non-trivial task, as investigators must locate relevant search hits amongst millions of investigatively non-relevant hits that are in-fact responsive to the search query. This emergent research tackles the problem of exceedingly poor information retrieval overhead by reviewing extant web mining ranking algorithms, explaining why they cannot be simply extended to digital forensic text mining, and proposing a new digital forensic text mining ranking algorithm, using PageRank as its basis. Future work is on-going and focused on lexical ontology development and validating the proposed algorithm. Collapse

Topics: website digital forensics knowledge representation web page digital media

Methods: computational algorithm natural language processing ontological modelling web mining

Effect of Business Intelligence and Analytics on Business Performance

2016 | Americas Conference on Information Systems | Citations: 0

Authors: Kakhki, Mohammad Daneshvar; Palvia, Prashant

Abstract: This article examines the relationship between extent of business intelligence a ... Expand

Abstract: This article examines the relationship between extent of business intelligence and analytics (BI&A) implementation and business performance. Also, it analyzes the moderating role of technology in this relationship. The data for our model is collected from secondary data sources for 116 public companies in United States. The data is analyzed using structural equation modeling techniques. Our findings show positive relationship between extent of BI&A implementation and business performance. Furthermore, our results show that type of BI&A has significant moderating impact on the BI&A implementation and performance relationship. Collapse

Topics: analytical information system organizational productivity LinkedIn human resource management IT investment

Methods: LexisNexis PLS tool Compustat computational algorithm partial least squares regression

Big data: From beginning to future

2016 | International Journal of Information Management | Citations: 31

Authors: Yaqoob, Ibrar; Hashem, Ibrahim Abaker Targio; Gani, Abdullah; Mokhtar, Salimah; Ahmed, Ejaz; Anuar, Nor Badrul; Vasilakos, Athanasios V.

Abstract: a b s t r a c tBig data is a potential research area receiving considerable att ... Expand

Abstract: a b s t r a c tBig data is a potential research area receiving considerable attention from academia and IT communities. In the digital world, the amounts of data generated and stored have expanded within a short period of time. Consequently, this fast growing rate of data has created many challenges. In this paper, we use structuralism and functionalism paradigms to analyze the origins of big data applications and its current trends. This paper presents a comprehensive discussion on state-of-the-art big data technologies based on batch and stream data processing. Moreover, strengths and weaknesses of these technologies are analyzed. This study also discusses big data analytics techniques, processing methods, some reported case studies from different vendors, several open research challenges, and the opportunities brought about by big data. The similarities and differences of these techniques and technologies based on important parameters are also investigated. Emerging technologies are recommended as a solution for big data problems. Collapse

Topics: big data distributed computing cryptographic hash function parallel computing Cassandra

Methods: case study web mining machine learning social network analysis computational algorithm

Recommender system application developments: A survey

2015 | Decision Support Systems | Citations: 48

Authors: Lu, Jie; Wu, Dianshuang; Mao, Mingsong; Wang, Wei; Zhang, Guangquan

Abstract: A recommender system aims to provide users with personalized online product or s ... Expand

Abstract: A recommender system aims to provide users with personalized online product or service recommendations to handle the increasing online information overload problem and improve customer relationship management. Various recommender system techniques have been proposed since the mid-1990s, and many sorts of recommender system software have been developed recently for a variety of applications. Researchers and managers recognize that recommender systems offer great opportunities and challenges for business, government, education, and other domains, with more recent successful developments of recommender systems for real-world applications becoming apparent. It is thus vital that a high quality, instructive review of current trends should be conducted, not only of the theoretical research results but more importantly of the practical developments in recommender systems. This paper therefore reviews up-to-date application developments of recommender systems, clusters their applications into eight main categories: e-government, e-business, e-commerce/e-shopping, e-library, e-learning, e-tourism, e-resource services and e-group activities, and summarizes the related recommendation techniques used in each category. It systematically examines the reported recommender systems through four dimensions: recommendation methods (such as CF), recommender systems software (such as BizSeeker), real-world application domains (such as e-business) and application platforms (such as mobile-based platforms). Some significant new topics are identified and listed as new directions. By providing a state-of-the-art knowledge, this survey will directly support researchers and practical professionals in their understanding of developments in recommender system applications. Collapse

Topics: recommender system systems development electronic business electronic commerce government system

Methods: cluster analysis survey web mining case study literature sample

Theories: fuzzy set theory