Harnani Mat Zin, N. Mustapha, M. A. Azmi Murad, Nurfadhlina Mohd Sharef
{"title":"A Meta-heuristic Algorithm for the Minimal High-Quality Feature Extraction of Online Reviews","authors":"Harnani Mat Zin, N. Mustapha, M. A. Azmi Murad, Nurfadhlina Mohd Sharef","doi":"10.32890/jict2022.21.4.5","DOIUrl":"https://doi.org/10.32890/jict2022.21.4.5","url":null,"abstract":"Feature extraction and selection are critical in sentiment analysis (SA) to extract and select only the appropriate features by removing those deemed redundant. As such, the successful implementation of this process leads to better classification accuracy. Inevitably, selecting high-quality minimal features can be challenging given the inherent complication in dealing with over-fitting issues. Most of the current studies used a heuristic method to perform the classification process that will result in selecting and examining only a single feature subset, while ignoring the other subsets that might give better results. This study explored the effect of using the meta-heuristic method together with the ensemble classification method in the sentiment classification of online reviews. Adding to that point, the extraction and selection of relevant features used feature ranking, hyper-parameter optimization, crossover, and mutation, while the classification process utilized the ensemble classifier. The proposed method was tested on the polarity movie review dataset v2.0 and product review dataset (books, electronics, kitchen, and music). The test results indicated that the proposed method significantly improved the classification results by 94%, which far exceeded the existing method. Therefore, the proposed feature extraction and selection method can help in improving the performance of SA in online reviews and, at the same time, reduce thenumber of extracted features. ","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89937731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Comparison between Standardized Mortality Ratio, Poisson-Gamma and Stochastic Sic Model for Pneumonia Disease Mapping in Malaysia","authors":"Ijlal Mohd Diah, Nazrina Aziz","doi":"10.32890/jict2022.21.4.4","DOIUrl":"https://doi.org/10.32890/jict2022.21.4.4","url":null,"abstract":"Pneumonia is one of the primary causes of death from infectious diseases. Traditionally, its spread has been tracked based on thetotal number of cases reported, with no concern for geographical distribution. Disease mapping is among the ways public health andthe government can monitor diseases as a preventative strategy. Clear pictures of the risk areas can be seen using this method. Relative risk estimation is a significant part of disease mapping that needs to be considered when studying disease occurrence. This paper aimed to estimate the relative risk values for pneumonia based on three models and compare the results. The approaches used in this study were Standardized Morbidity Ratio (SMR), Poisson-gamma, and discrete time-space stochastic Susceptible-Infected-Carriers (SIC) models, which were applied in estimating the relative risk values. Results showed that Kuala Lumpur was classified as a very low-risk area for pneumonia incidence when using the SMR and Poisson-gamma models. In contrast, Selangor was identified as a very low-risk area when using the discrete time-space stochastic SIC model. Putrajaya was categorised as a very high-risk area in the results of all three types of methods. In conclusion, this stochastic SIC model demonstrated better performance than the conventional models.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88930579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nur Syamimi Muhamad Fauzi, M. Mat Kasim, Noryatimah Mat Desa
{"title":"Construction of Air Pollution Index with the Inclusion of Aggregated Weights of the Pollutants","authors":"Nur Syamimi Muhamad Fauzi, M. Mat Kasim, Noryatimah Mat Desa","doi":"10.32890/jict2022.21.4.2","DOIUrl":"https://doi.org/10.32890/jict2022.21.4.2","url":null,"abstract":"The ambient air quality measurement in Malaysia is described as Air Pollution Index (API). Basically the existing API for a given period of time is defined as the maximum value of the sub-index values of six pollutants. Although research has shown that long and short term exposure to air suspended toxicants has a different toxicological impact on human, the API still considers these pollutants as having equal hazardous impacts on human. Hence, this paper aims to propose a new API that includes weights representing different hazardous levels of these pollutants in its calculation. Based on secondary data of six pollutants’ readings for sixteen states of Malaysia for year 2018, the aggregated weights were computed by combining both weights obtained from the subjective experts’ opinions and the objective data-driven methods, which balanced both perspectives of evaluations. The results show that the particulate matter with aerodynamic diameter less than 2.5 micrometre (PM2.5) found to be the most hazardous pollutant since its aggregated weight value is the highest and the distributions of the API readings for all sixteen states were found to be normal. The highest and lowest API readings took place on the 14th of August and 10 of March 2018 respectively. It is argued that the new API readings are more accurate and give a better picture about the occurrence of air pollution in Malaysia in particular. This study provides a new insight in constructing API specifically and contributes a more comprehensive and precise air quality measurements to be analysed by the responsible authorities in their efforts towards healthy environment.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74042669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
N. Hashim, Norhanisha Yusof, A. Hussain, M. Ibrahim
{"title":"User Experience Dimensions for E-procurement","authors":"N. Hashim, Norhanisha Yusof, A. Hussain, M. Ibrahim","doi":"10.32890/jict2022.21.4.1","DOIUrl":"https://doi.org/10.32890/jict2022.21.4.1","url":null,"abstract":"The use of e-procurement is needed for business transactions, especially regarding procurement activities. However, system usersalways demand and expect to use the system without problems. Existing studies on e-procurement do not focus on user experience(UX). Only a few studies have identified dimensions for UX evaluation; however, they are for e-government online services and construction. Identifying the UX dimensions for e-procurement is important for measuring user experience to provide better services. Therefore, this study attempted to investigate and determine the dimensions of user experience for e-procurement. The method for selecting articles was adopted from the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA). The study analysed the data using thematic analysis based on the Systems and software Quality Requirements and Evaluation (SQuaRE) standards, such as ISO 25022:2016 and ISO 25023:2016, as guidance. The findings showed that among the most used UX dimensions in the e-procurement literature were satisfaction, security, transparency, efficiency, and reliability. Other UX-related dimensions identified from the review were usability, compatibility, effectiveness, performance efficiency, functional suitability, attractiveness, explainability, fairness, and visibility. The study was conducted to identify the UX dimensions for e-procurement from literature studies by organising them using ISO 25022:2016 and ISO 25023:2016 standards. This study could serve as a guideline for designers, developers, and researchers to develop an e-procurement system by referring to the proposed UX dimensions to produce a positive user experience. Moreover, the findings are beneficial to practitioners on software quality attributes.","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79237441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Azam sadta Mortazavi kahangi, P. Saketi, J. Mehrabi
{"title":"Drivers, Obstacles and consequences of digital entrepreneurship in Iran's\u0000 road freight transportation industry","authors":"Azam sadta Mortazavi kahangi, P. Saketi, J. Mehrabi","doi":"10.52547/jict.42100.15.56.1","DOIUrl":"https://doi.org/10.52547/jict.42100.15.56.1","url":null,"abstract":"The purpose of this research is to identify the drivers, obstacles and consequences of digital entrepreneurship in Iran's road freight transportation industry. The statistical society of this research in the qualitative part was made up of 20 experts in this field who were selected using non-random sampling method. In the quantitative part, using Cochran's formula and cluster sampling method, 170 employees of this industry were selected as samples. In order to collect data, a semi-structured interview was used in the qualitative part and a researcher-made questionnaire was used in the quantitative part, whose validity and reliability were checked and confirmed. In the data analysis, systematic literature review and coding and Maxqda software were used in the qualitative part, and inferential statistics and SPSS and Lisrel software were used in the quantitative part. Finally, 9 indicators in 4 driver factors, 11 indicators in 3 obstacle factors and 55 indicators in 8 consequence categories were extracted and prioritized using factor analysis. The result of this research shows that the political component is a priority as a driver and political obstacles are a priority as an obstacle. Therefore, the role of the government in this field is very important .","PeriodicalId":39396,"journal":{"name":"International Journal of Information and Communication Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82300328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}