The Experts below are selected from a list of 20493 Experts worldwide ranked by ideXlab platform
Ahmad Kamal - One of the best experts on this subject based on the ideXlab platform.
-
review mining for feature based opinion summarization and visualization
International Journal of Computer Applications, 2015Co-Authors: Ahmad KamalAbstract:business Intelligence, Product recommendation, targeted marketing etc. have fascinated many research attentions around the globe. Various research efforts attempted to mine opinions from customer reviews at different levels of granularity, including word-, sentence-, and document-level. However, development of a fully automatic opinion mining and sentiment analysis system is still elusive. Though the development of opinion mining and sentiment analysis systems are getting momentum, most of them attempt to perform document-level sentiment analysis, classifying a review document as positive, negative, or neutral. Such document-level opinion mining approaches fail to provide insight about users’ sentiment on individual features of a Product or service. Therefore, it seems to be a great help for both customers and manufacturers, if the reviews could be processed at a finer-grained level and presented in a summarized form through some visual means, highlighting individual features of a Product and users sentiment expressed over them. In this paper, the design of a unified opinion mining and sentiment analysis framework is presented at the intersection of both machine learning and natural language processing approaches. Also, design of a novel feature-level review summarization scheme is proposed to visualize mined features, opinions and their polarity values in a comprehendible way.
-
review mining for feature based opinion summarization and visualization
arXiv: Information Retrieval, 2015Co-Authors: Ahmad KamalAbstract:The application and usage of opinion mining, especially for business Intelligence, Product recommendation, targeted marketing etc. have fascinated many research attentions around the globe. Various research efforts attempted to mine opinions from customer reviews at different levels of granularity, including word-, sentence-, and document-level. However, development of a fully automatic opinion mining and sentiment analysis system is still elusive. Though the development of opinion mining and sentiment analysis systems are getting momentum, most of them attempt to perform document-level sentiment analysis, classifying a review document as positive, negative, or neutral. Such document-level opinion mining approaches fail to provide insight about users sentiment on individual features of a Product or service. Therefore, it seems to be a great help for both customers and manufacturers, if the reviews could be processed at a finer-grained level and presented in a summarized form through some visual means, highlighting individual features of a Product and users sentiment expressed over them. In this paper, the design of a unified opinion mining and sentiment analysis framework is presented at the intersection of both machine learning and natural language processing approaches. Also, design of a novel feature-level review summarization scheme is proposed to visualize mined features, opinions and their polarity values in a comprehendible way.
Sitthipo Phichitphol - One of the best experts on this subject based on the ideXlab platform.
-
Supply Chain Business Intelligence and the Supply Chain Performance: The Mediating Role of Supply Chain Agility
International Journal of Supply Chain Management, 2020Co-Authors: Aunyawong Wissawa, Waiyawuththanapoom Phutthiwat, Pintuma Sittichai, Sitthipo PhichitpholAbstract:The study has planned to examine the impact of the supply chain business Intelligence on the supply chain performance of the Indonesian firms. Additionally, the study has examined the mediating role of agile capability and supply chain capability. For data gathering, total 450 questionnaires were distributed and obtained only 325 questionnaires. During data screening process 23 questionnaires were excluded, since they were incomplete. Therefore, we obtained 67% response rate for the survey in present study. Partial Least Square-Structural Equation Modeling (PLS-SEM) is an important statistical procedure to carry out multivariate data analysis, Empirical analysis in this study supports the supply chain business Intelligence competence with respect to technical, cultural and managerial competence. This indicates that it is necessary to utilize appropriate technologies and tools and have well-defined processes, although these are not sufficient conditions to develop business Intelligence Product efficiently and effectively, such as, relevant knowledge and information which facilitate in the decision-making functions of the supply chain. Besides, some inter- and intra-organizational culture elements also affect the business Intelligence Product creation. The prior research further supported the significance of knowledge/information-related competences to enhance agile performance characteristics and competitive performance of the supply chain
Aunyawong Wissawa - One of the best experts on this subject based on the ideXlab platform.
-
Supply Chain Business Intelligence and the Supply Chain Performance: The Mediating Role of Supply Chain Agility
International Journal of Supply Chain Management, 2020Co-Authors: Aunyawong Wissawa, Waiyawuththanapoom Phutthiwat, Pintuma Sittichai, Sitthipo PhichitpholAbstract:The study has planned to examine the impact of the supply chain business Intelligence on the supply chain performance of the Indonesian firms. Additionally, the study has examined the mediating role of agile capability and supply chain capability. For data gathering, total 450 questionnaires were distributed and obtained only 325 questionnaires. During data screening process 23 questionnaires were excluded, since they were incomplete. Therefore, we obtained 67% response rate for the survey in present study. Partial Least Square-Structural Equation Modeling (PLS-SEM) is an important statistical procedure to carry out multivariate data analysis, Empirical analysis in this study supports the supply chain business Intelligence competence with respect to technical, cultural and managerial competence. This indicates that it is necessary to utilize appropriate technologies and tools and have well-defined processes, although these are not sufficient conditions to develop business Intelligence Product efficiently and effectively, such as, relevant knowledge and information which facilitate in the decision-making functions of the supply chain. Besides, some inter- and intra-organizational culture elements also affect the business Intelligence Product creation. The prior research further supported the significance of knowledge/information-related competences to enhance agile performance characteristics and competitive performance of the supply chain
Dokman Tomislav - One of the best experts on this subject based on the ideXlab platform.
-
Analytical framework of open source Intelligence in counterterrorism
'Faculty of Humanities and Social Sciences University of Zagreb', 2021Co-Authors: Dokman TomislavAbstract:Smještena u području kritičkih sigurnosnih studija te informacijskih i komunikacijskih znanosti, ova disertacija ima osnovni cilj utvrditi predstavljaju li obavještajne informacije iz otvorenih izvora koristan izvor znanja u protuterorizmu i protuteroru. Jedinica analize je tako GTD baza koja je temeljena na podacima iz otvorenih izvora koja bilježi globalne terorističke udare od 1970. naovamo. Podjedinice su terorističke organizacije koje su selektirane prema geografskom kriteriju, zatim kriteriju tipologije terorizma i po kriteriju jedne terorističke organizacije s najvećim brojem zabilježenih terorističkih udara u vremenskom razdoblju od 1972. do 11. rujna 2001. i terorističke organizacije s najvećim brojem terorističkih udara u vremenskom razdoblju od 12. rujna 2001. do kraja 2017. U radu su utvrđena ključna obilježja obavještajnih informacija iz javo dostupne baze evidentiranih terorističkih udara u kreiranju obavještajnog proizvoda, ponajprije njihova pouzdanost, točnost, sustavnost, razumljivost, longitudinalnost, mogućnost obrade te njihov akcijabilni karakter. Istraživana primjena obavještajnih informacija iz otvorenih izvora u protuterorizmu ogleda se u pružanju kontekstualnih znanja o nekoj terorističkoj organizaciji, otkrivanju njezinog terenskog predznaka djelovanja, geoprostornom i vremenskom djelovanju, ciljevima napada i taktikama djelovanja. Ujedno, primjenjivost obavještajnih informacija iz otvorenih izvora u protuterorizmu očituje se i u detektiranju trendova i obrazaca ponašanja terorista, predviđanju budućih lokaliteta terora, otkrivanju snaga, prednosti, nedostataka i prilika terorističkih organizacija. Dok je s aspekta protuterora aplikativna vrijednost vidljiva prilikom izrade procjene rizika ugroženosti od terorizma, definiranja statusa sigurnosti konkretnog prostora i uspostavi mehanizama represije. Kako je polje istraživanja relativno novo, s još neriješenim terminološkim i teorijskim problemima, u prvoj fazi se pristupa identificiranju ključnih termina. Nakon analize dostupne literature, za svaki od pojmova (Intelligence i open source Intelligence) predlaže se prijevod koji će ujedno biti i operacionalni u daljnjem istraživanju. Istraživanjem se nastoji premostiti problem nepostojanja jedinstvene definicije pojma obavještajno što predstavlja sporno mjesto u postojećem obavještajnom znanju. Kako bi se došlo do operacionalne definicije rada, odnosno ključnih obilježja pojma, korištena je metoda analize i sinteze postojećeg znanja u području informacijskih znanosti i obavještajnih studija. Na temelju konstruirane baze postojećih definicija pojma obavještajno, njih 50, korištenjem kvalitativne i kvantitativne metodologije (analize sadržaja i frekvencijske analize) konstruirana je definicija pojma obavještajno. Na temelju izlučenih konstitutivnih elemenata, obavještajno podrazumijeva prikupljenu i analitički obrađenu informaciju namijenjenu krajnjim korisnicima za donošenje odluka.Located in the field of critical security studies and information and communication sciences, this dissertation has a main goal to determine does open source Intelligence present Productive resource of knowledge in counterterrorism and in counterterror. The unit of analysis is an opensource database (GTD), that records global terrorist events since the 1970. Subunits are terrorist organizations that are selected according to the geographic criteria; a terrorist organization from Europe, South America, Africa and Asia, then the criteria of typology of terrorism; one fundamentalist and one secular terrorist organization and a terrorist organization with the highest number of terrorist attacks recorded over the period from 1972 to 11 September 2001, and a terrorist organization with the highest number of terrorist attacks in the period from 12 September 2001 to the end of 2017. We identified key features of Intelligence from publicly available database, which consists of recorded terrorist attacks, in the creation of an Intelligence Product, primarily their reliability, accuracy, coherence, comprehensibility, longitudinality, data processing capability, simplicity of data presentation and usage of analytical techniques for further utilization and their actionable character. The researched application of open source Intelligence in counterterrorism is reflected in providing of contextual knowledge about a terrorist organization, detection of its national or supranational characteristics, geospatial and temporal activity, target focus and terrorist modus operandi. The applicability of open source Intelligence in counterterrorism is manifested as well in detecting trends and patterns of terrorist behavior, predicting future locations of terrorist activity, revealing the strengths, advantages, disadvantages and opportunities of terrorist organizations. While from the aspect of counterterror, the applicative value of open source Intelligence is visible when assessing the risk of terrorist threat, defining the security status of a specific area and establishing mechanisms of repression from the spectrum of counterterror. As the subject of research is rather new with unsettled terminological and theoretical problems in the first stage we authenticate central terms. After analyzing the available literature we nominate translation for each of the terms (Intelligence and open source Intelligence), which version will be operational throughout the research. In order to achive an operational definition of work, i.e. key features of the term, content analysis and synthesis of exsisting knowledge in the field of information sciences and Intelligence studies was used. Based on constructed database of exsisting definitions of Intelligence (N=50), we use qualitative and quantitative methodology (content and frequency analysis) to propose a new definition of term Intelligence. According to excluded constitutive elements, definition of Intelligence stands for collected and analyzed information created for end users in order to make decisions
Vince I Madai - One of the best experts on this subject based on the ideXlab platform.
-
from bit to bedside a practical framework for artificial Intelligence Product development in healthcare
arXiv: Computers and Society, 2020Co-Authors: David Higgins, Vince I MadaiAbstract:Artificial Intelligence (AI) in healthcare holds great potential to expand access to high-quality medical care, whilst reducing overall systemic costs. Despite hitting the headlines regularly and many publications of proofs-of-concept, certified Products are failing to breakthrough to the clinic. AI in healthcare is a multi-party process with deep knowledge required in multiple individual domains. The lack of understanding of the specific challenges in the domain is, therefore, the major contributor to the failure to deliver on the big promises. Thus, we present a decision perspective framework, for the development of AI-driven biomedical Products, from conception to market launch. Our framework highlights the risks, objectives and key results which are typically required to proceed through a three-phase process to the market launch of a validated medical AI Product. We focus on issues related to Clinical validation, Regulatory affairs, Data strategy and Algorithmic development. The development process we propose for AI in healthcare software strongly diverges from modern consumer software development processes. We highlight the key time points to guide founders, investors and key stakeholders throughout their relevant part of the process. Our framework should be seen as a template for innovation frameworks, which can be used to coordinate team communications and responsibilities towards a reasonable Product development roadmap, thus unlocking the potential of AI in medicine.