Search results
1 – 10 of 10Vimala Balakrishnan, Luqman Hakim Abdul Rahman, Jia Kai Tan and Yee Sin Lee
This systematic review aims to synthesize the literature reporting the motives, sociodemographic, attitude/behavior and impacts of fake news during the COVID-19 pandemic…
Abstract
Purpose
This systematic review aims to synthesize the literature reporting the motives, sociodemographic, attitude/behavior and impacts of fake news during the COVID-19 pandemic, targeting the general population worldwide.
Design/methodology/approach
A systematic review approach was adopted based on PRISMA, targeting articles published in five databases from January 2020 to November 2021. The screening resulted in 46 eligible papers.
Findings
Results indicate low level of awareness, knowledge, media/health literacy, low trust in science/scientists and entertainment/socialization to be the main motivating drivers for fake news dissemination, whereas the phenomenon is more prominent among those with low socio-economic status, and males. Negative impacts were reported due to fake news dissemination, especially violation to precautionary measures, negative affections, and low trust in government/news, with many believing that others are more susceptible to fake news than themselves.
Social implications
Considering the pandemic is still on-going and the deleterious consequences of fake news, there is a need for cohort-based interventions from the concerned authorities.
Originality/value
The systematic review covers a wide timeline of 23 months (i.e. up to end of 2022) targeting five well-known databases, hence articles examined are deemed extensive and comprehensive. The review specifically focused on the general population with results revealing interesting motives, sociodemographic profiles, attitude and impact of this phenomenon during the COVID-19 pandemic.
Peer review
The peer review history for this article is available at: https://publons.com/publon/10.1108/OIR-02-2022-0082.
Details
Keywords
Vimala Balakrishnan, Aainaa Nadia Mohammed Hashim, Voon Chung Lee, Voon Hee Lee and Ying Qiu Lee
This study aims to develop a machine learning model to detect structure fire fatalities using a dataset comprising 11,341 cases from 2011 to 2019.
Abstract
Purpose
This study aims to develop a machine learning model to detect structure fire fatalities using a dataset comprising 11,341 cases from 2011 to 2019.
Design/methodology/approach
Exploratory data analysis (EDA) was conducted prior to modelling, in which ten machine learning models were experimented with.
Findings
The main fatal structure fire risk factors were fires originating from bedrooms, living areas and the cooking/dining areas. The highest fatality rate (20.69%) was reported for fires ignited due to bedding (23.43%), despite a low fire incident rate (3.50%). Using 21 structure fire features, Random Forest (RF) yielded the best detection performance with 86% accuracy, followed by Decision Tree (DT) with bagging (accuracy = 84.7%).
Research limitations/practical implications
Limitations of the study are pertaining to data quality and grouping of categories in the data pre-processing stage, which could affect the performance of the models.
Originality/value
The study is the first of its kind to manipulate risk factors to detect fatal structure classification, particularly focussing on structure fire fatalities. Most of the previous studies examined the importance of fire risk factors and their relationship to the fire risk level.
Details
Keywords
Prabha Rajagopal, Sri Devi Ravana, Yun Sing Koh and Vimala Balakrishnan
The effort in addition to relevance is a major factor for satisfaction and utility of the document to the actual user. The purpose of this paper is to propose a method in…
Abstract
Purpose
The effort in addition to relevance is a major factor for satisfaction and utility of the document to the actual user. The purpose of this paper is to propose a method in generating relevance judgments that incorporate effort without human judges’ involvement. Then the study determines the variation in system rankings due to low effort relevance judgment in evaluating retrieval systems at different depth of evaluation.
Design/methodology/approach
Effort-based relevance judgments are generated using a proposed boxplot approach for simple document features, HTML features and readability features. The boxplot approach is a simple yet repeatable approach in classifying documents’ effort while ensuring outlier scores do not skew the grading of the entire set of documents.
Findings
The retrieval systems evaluation using low effort relevance judgments has a stronger influence on shallow depth of evaluation compared to deeper depth. It is proved that difference in the system rankings is due to low effort documents and not the number of relevant documents.
Originality/value
Hence, it is crucial to evaluate retrieval systems at shallow depth using low effort relevance judgments.
Details
Keywords
Elham Majd, Vimala Balakrishnan and Vahid Godazgar
This paper aims to enhance the successful interaction between buyers and suppliers who use intelligent agents by presenting a computational model to detect the most reliable…
Abstract
Purpose
This paper aims to enhance the successful interaction between buyers and suppliers who use intelligent agents by presenting a computational model to detect the most reliable supplier agent according to advice of an advisor agent.
Design/methodology/approach
In this case, the authors study the most representative models in agent environments. According to these analysis criteria, a computational model was presented to compute the reliability of supplier agents and then select the most reliable one. To evaluate the proposed method, the experimentation was carried out in two stages. First, the average accuracy of model in computing the reliability was evaluated by comparing a random selection method. Second, the performance of the model in detecting the most reliable supplier was evaluated in an agent environment by applying trust network game as a simulator.
Findings
The experimental results revealed that the proposed method can detect the most reliable supplier accurately in both consistent and oscillating agent environments.
Originality/value
The authors believe that the proposed model will be beneficial to enhance the fulfillment of purchasing between buyers and suppliers.
Details
Keywords
Wandeep Kaur and Vimala Balakrishnan
The purpose of this paper is to investigate the effect of including letter repetition commonly found within social media text and its impact in determining the sentiment scores…
Abstract
Purpose
The purpose of this paper is to investigate the effect of including letter repetition commonly found within social media text and its impact in determining the sentiment scores for two major airlines in Malaysia.
Design/methodology/approach
A Sentiment Intensity Calculator (SentI-Cal) was developed by assigning individual weights to each letter repetition, and tested it using data collected from official Facebook pages of the airlines.
Findings
Evaluation metrics indicate that SentI-Cal outperforms the baseline tool Semantic Orientation Calculator (SO-CAL), with an accuracy of 90.7 percent compared to 58.33 percent for SO-CAL.
Practical implications
A more accurate sentiment score allows airline services to easily obtain a better understanding of the sentiments of their customers, hence providing opportunities in improving their airline services.
Originality/value
Proposed mechanism calculates sentiment intensity of social media text by assigning individual weightage to each repeated letter and exclamation mark thus producing a more accurate sentiment score.
Details
Keywords
Yasir Mehmood and Vimala Balakrishnan
Research on sentiment analysis were mostly conducted on product and services, resulting in scarcity of studies focusing on social issues, which may require different mechanisms…
Abstract
Purpose
Research on sentiment analysis were mostly conducted on product and services, resulting in scarcity of studies focusing on social issues, which may require different mechanisms due to the nature of the issue itself. This paper aims to address this gap by developing an enhanced lexicon-based approach.
Design/methodology/approach
An enhanced lexicon-based approach was employed using General Inquirer, incorporated with multi-level grammatical dependencies and the role of verb. Data on illegal immigration were gathered from Twitter for a period of three months, resulting in 694,141 tweets. Of these, 2,500 tweets were segregated into two datasets for evaluation purposes after filtering and pre-processing.
Findings
The enhanced approach outperformed ten online sentiment analysis tools with an overall accuracy of 81.4 and 82.3% for dataset 1 and 2, respectively as opposed to ten other sentiment analysis tools.
Originality/value
The study is novel in the sense that data pertaining to a social issue were used instead of products and services, which require different mechanism due to the nature of the issue itself.
Details
Keywords
Choon Boey Lim, Duncan Bentley, Fiona Henderson, Shin Yin Pan, Vimala Devi Balakrishnan, Dharshini M. Balasingam and Ya Yee Teh
The purpose of this paper is to examine issues academics at importing institutions face while delivering Australian degrees in Malaysia. Transnational higher education (TNE) has…
Abstract
Purpose
The purpose of this paper is to examine issues academics at importing institutions face while delivering Australian degrees in Malaysia. Transnational higher education (TNE) has been widely researched. However, less widely researched is the area of understanding what academics at the offshore locations need to uphold the required academic standards of their partnered exporting universities. This area warrants close attention if Australian and other transnational education universities are to sustain their growth through a partnership model with offshore academics delivering a portion (often a substantial portion) of the teaching.
Design/methodology/approach
Two focus groups were conducted with a mix of long standing and newly recruited Malaysian lecturers who taught into an Australian degree through a partnership arrangement. The semi-structured questions which were used were derived from a preliminary literature review and previous internal institutional reports.
Findings
The findings from the focus groups indicate that TNE is largely “Australian-centric” when addressing the standard of academic quality and integrity. The findings pointed not so much to any sustained internationalisation of curriculum or administration or personnel but more as internationalisation as deemed required by the local academic.
Originality/value
To a greater extent, the findings highlighted that equivalent student outcomes do not necessarily equate to equivalent learning experiences or teaching workload. In fact, the frustration of the interviewees on the tension to fulfil the home institution curriculum and helping students to “comprehend” an Australian-centric curriculum translates to “additional and unrecognised workload” for the interviewees.
Details
Keywords
Vimala Balakrishnan, Kian Ahmadi and Sri Devi Ravana
– The purpose of this paper is to improve users’ search results relevancy by manipulating their explicit feedback.
Abstract
Purpose
The purpose of this paper is to improve users’ search results relevancy by manipulating their explicit feedback.
Design/methodology/approach
CoRRe – an explicit feedback model integrating three popular feedback, namely, Comment-Rating-Referral is proposed in this study. The model is further enhanced using case-based reasoning in retrieving the top-5 results. A search engine prototype was developed using Text REtrieval Conference as the document collection, and results were evaluated at three levels (i.e. top-5, 10 and 15). A user evaluation involving 28 students was administered, focussing on 20 queries.
Findings
Both Mean Average Precision and Normalized Discounted Cumulative Gain results indicate CoRRe to have the highest retrieval precisions at all the three levels compared to the other feedback models. Furthermore, independent t-tests showed the precision differences to be significant. Rating was found to be the most popular technique among the participants, producing the best precision compared to referral and comments.
Research limitations/implications
The findings suggest that search retrieval relevance can be significantly improved when users’ explicit feedback are integrated, therefore web-based systems should find ways to manipulate users’ feedback to provide better recommendations or search results to the users.
Originality/value
The study is novel in the sense that users’ comment, rating and referral were taken into consideration to improve their overall search experience.
Details
Keywords
Sri Devi Ravana, Prabha Rajagopal and Vimala Balakrishnan
In a system-based approach, replicating the web would require large test collections, and judging the relevancy of all documents per topic in creating relevance judgment through…
Abstract
Purpose
In a system-based approach, replicating the web would require large test collections, and judging the relevancy of all documents per topic in creating relevance judgment through human assessors is infeasible. Due to the large amount of documents that requires judgment, there are possible errors introduced by human assessors because of disagreements. The paper aims to discuss these issues.
Design/methodology/approach
This study explores exponential variation and document ranking methods that generate a reliable set of relevance judgments (pseudo relevance judgments) to reduce human efforts. These methods overcome problems with large amounts of documents for judgment while avoiding human disagreement errors during the judgment process. This study utilizes two key factors: number of occurrences of each document per topic from all the system runs; and document rankings to generate the alternate methods.
Findings
The effectiveness of the proposed method is evaluated using the correlation coefficient of ranked systems using mean average precision scores between the original Text REtrieval Conference (TREC) relevance judgments and pseudo relevance judgments. The results suggest that the proposed document ranking method with a pool depth of 100 could be a reliable alternative to reduce human effort and disagreement errors involved in generating TREC-like relevance judgments.
Originality/value
Simple methods proposed in this study show improvement in the correlation coefficient in generating alternate relevance judgment without human assessors while contributing to information retrieval evaluation.
Details
Keywords
Elham Majd and Vimala Balakrishnan
The purpose of this paper is to enhance trust in multi-agent systems by presenting a new computational model, named reputation-distribute-conflict (R-D-C), to select the most…
Abstract
Purpose
The purpose of this paper is to enhance trust in multi-agent systems by presenting a new computational model, named reputation-distribute-conflict (R-D-C), to select the most trustworthy provider agent based on computing reputation, disrepute, and conflict of each provider agent.
Design/methodology/approach
R-D-C propose based on three vital components for evaluating trustworthiness of providers as reputation, disrepute, and conflict, where disrepute is a component almost all trust models ignored. The R-D-C model presents a computational method for evaluating to select the most trustworthy provider agent. In order to evaluate the R-D-C model, the experimentation was carried out in two stages, by designing a simulated multi-agent environment. First, the accuracy of the R-D-C model in computing R-D-C was investigated. Second, the performance of the model was compared with other existing trust models. Moreover, comparison of the performance of the R-D-C model with other models demonstrates that the R-D-C model performs significantly better than the other models. Therefore, the R-D-C model is capable of evaluating the trustworthiness of agents more accurately and it can select the most trustworthy provider better than the other models.
Findings
The results show that the R-D-C model works well in different multi-agent environments, even when the number of untrustworthy providers is higher than that of the trustworthy ones.
Originality/value
The R-D-C model is useful for researchers to enhance the safety of online transactions in multi-agent environments, especially if the researchers explore more components; in fact the R-D-C model is capable of adding these new components and selects the most trustworthy provider agent.
Details