Research

1. To Train or Not to Train? How Training Affects the Diversity of Crowdsourced Data. Forty-First International Conference on Information Systems (ICIS), India 2020. With Jeffrey Parsons and Roman Lukyanenko

Organizations and individuals who use crowdsourcing to collect data prefer knowledgeable contributors. They train recruited contributors, expecting them to provide better quality data than untrained contributors. However, selective attention theory suggests that, as people learn the characteristics of a thing, they focus on only those characteristics needed to identify the thing, ignoring others. In observational crowdsourcing, selective attention might reduce data diversity, limiting opportunities to repurpose and make discoveries from the data. We examine how training affects the diversity of data in a citizen science experiment. Contributors, divided into explicitly and implicitly trained groups and an untrained (control) group, reported artificial insect sightings in a simulated crowdsourcing task. We found that trained contributors reported less diverse data than untrained contributors, and explicit (rule-based) training resulted in less diverse data than implicit (exemplar-based) training. We conclude by discussing implications for designing observational crowdsourcing systems to promote data repurposability.

Publication

2. Ogunseye, S., Parsons, J., & Lukyanenko, R. (2020). Crowdsourcing for Repurposable Data: What We Lose When We Train Our Crowds. AIS SIGSAND.

Users of crowdsourced data expect that knowledge of the domain of a data crowdsourcing task will positively affect the data that their contributors provide, so they train potential participants on the crowdsourcing task to be performed. We carried out an experiment to test how training affects data quality and data repurposability – the capacity for data to flexibly accommodate both anticipated and unanticipated uses. Eighty-four contributors trained explicitly (using rules), implicitly (using exemplars), and untrained, report the sighting of artificial insects and other entities in a simulated citizen science project. We find that there are no information quality or data repurposability advantages to training contributors. Trained contributors reported fewer differentiating attributes of entities and fewer total attributes of the entities they observed. Trained contributors are therefore less likely to report data that can lead to discoveries. We discuss the implications of our findings to the design of inclusive data crowdsourcing systems.

Publication

3. Ogunseye, S., & Parsons, J. (2018). Designing for Information Quality in the Era of Repurposable Crowdsourced User-Generated Content. International Conference on Advanced Information Systems Engineering (pp. 180-185). Springer, Cham.

Conventional wisdom holds that expert contributors provide higher quality user-generated content (UGC) than novices. Using the cognitive construct of selective attention, we argue that this may not be the case in some crowd-sourcing UGC applications. We argue that crowdsourcing systems that seek participation mainly from contributors who are experienced or have high levels of proficiency in the crowdsourcing task will gather less diverse and therefore less repurposable data. We discuss the importance of the information diversity dimension of information quality for the use and repurposing of UGC and provide a theoretical basis for our position, with the goal of stimulating empirical research.

Publication

4. Are Frequent Online Reviewers Really Helping? How Experience Affects the Attribute Diversity of Online Reviews. 20th annual Aldrich Conference, St. John’s, NL, Canada

5. Ogunseye, S., Parsons, J., & Lukyanenko, R. (2017). Do crowds go stale? Exploring the effects of crowd reuse on data diversity. WITS 2017.

Crowdsourcing is increasingly used to engage people to contribute data for a variety of purposes to support decision-making and analysis. A common assumption in many crowdsourcing projects is that experience leads to better contributions. In this research, we demonstrate limits of this assumption. We argue that greater experience in contributing to a crowdsourcing project can lead to a narrowing in the kind of data a contributor provides, causing a decrease in the diversity of data provided. We test this proposition using data from two sources-comments submitted with contributions in a citizen science crowdsourcing project, and three years of online product reviews. Our analysis of comments provided by contributors shows that the length of comments decreases as the number of contributions increases. Also, we find that the number of attributes reported by contributors decreases as they gain experience. These finding support our prediction, suggesting that the diversity of data provided by contributors declines over time.

Publication

6. Ogunseye, S., & Parsons, J. (2017). What Makes a Good Crowd? Rethinking the Relationship between Recruitment Strategies and Data Quality in Crowdsourcing. In Proceedings of the 16th AIS SIGSAND Symposium (pp. 19-20).

Conventional wisdom dictates that the quality of data collected in a crowdsourcing project is positively related to how knowledgeable the contributors are. Consequently, numerous crowdsourcing projects implement crowd recruitment strategies that reflect this reasoning. In this paper, we explore the effect of crowd recruitment strategies on the quality of crowdsourced data using classification theory. As these strategies are based on knowledge, we consider how a contributor’s knowledge may affect the quality of data he or she provides. We also build on previous research by considering relevant dimensions of data quality beyond accuracy and predict the effects of available recruitment strategies on these dimensions of data quality.

Publication

7. The Downside of Expertise: Does Domain Knowledge affect the Quality of Crowdsourced Data? Proceedings of the 15th AIS SIGSAND Symposium. With Jeffrey Parsons

Subject matter expertise is widely believed to have a positive effect on information quality in crowdsourcing. Many crowdsourcing systems are therefore designed to seek out contributions from experts in the crowd. We argue that expert contributors of data in crowdsourcing projects are proficient rule-based classifiers, and are efficient because they attend only to attributes of instances that are relevant to a classification task while ignoring attributes irrelevant to the task at hand. We posit that this selective attention will negatively affect the tendency of experts to contribute data outside of categories anticipated in the design of a class-based data crowdsourcing platform. We propose hypotheses derived from this view, and outline two experiments to test them. We conclude by discussing the potential implications of this work for the design of crowdsourcing platforms and the recruitment of expert versus novice data contributors in studies of data quality in crowdsourcing settings.

Publication

8. Ogunseye, S., & Parsons, J. (2016). Can expertise impair the quality of crowdsourced data? In SIGOPEN Developmental Workshop at ICIS.

It is not uncommon for projects that collect crowdsourced data to be commissioned with incomplete knowledge of data contributors, data consumers, and/or the purposes for which the data collected are going to be used. Such unanticipated uses and users of data form the basis for open information environments (OIEs), and the information collected through systems designed to gather content from users have high quality when they are complete, accurate, current and provided in an appropriate format. However, as it is assumed that experts provide higher quality information, many types of OIEs have been designed for experts. In this paper, we question the appropriateness of this assumption in the context of citizen science systems – an exemplary category of OIE. We begin by arguing that experts are primarily efficient rule-based classifiers, which implies that they selectively focus only on attributes relevant to their classification task and ignore others. Drawing from existing literature, we posit that experts’ focus on only diagnostic features of an entity leads to a learned inattention to non-diagnostic attributes. This may improve the accuracy of the information provided, but at the expense of its completeness, currency, format and ultimately the novelty (for unanticipated uses) of information provided. On the other hand, we predict that non-experts and amateurs may use rules to a lesser extent, resulting in less selective attention and leading them to provide more novel information with less trade-off of one dimension of information quality for another. We propose hypotheses derived from this view, and outline two experiments we have designed to test them across four dimensions of information quality. We conclude by discussing the potential implications of this work for the design of crowdsourcing platforms and the recruitment of experts, amateurs, or novice data contributors in studies of data quality in crowdsourcing settings.

Publication
Video

9. Preventing Social Engineering and Espionage in Collaborative Knowledge Management Systems (KMSs), Adoption of Virtual Technologies for Business, Educational, and Governmental Advancements, IGI. With Olusegun Folorunso and Jeff Zhang

Insider attack and espionage on computer-based information is a major problem for business organizations and governments. Knowledge Management Systems (KMSs) are not exempt from this threat. Prior research presented the Congenial Access Control Model (CAC), a relationship-based access control model, as a better access control method for KMS because it reduces the adverse effect of stringent security measures on the usability of KMSs. However, the CAC model, like other models, e.g., Role Based Access Control (RBAC), Time-Based Access Control (TBAC), and History Based Access Control (HBAC), does not provide adequate protection against privilege abuse by authorized users that can lead to industrial espionage. In this paper, the authors provide an Espionage Prevention Model (EP) that uses Semantic web-based annotations on knowledge assets to store relevant information and compares it to the FriendOf-A-Friend (FOAF) data of the potential recipient of the resource. It can serve as an additional layer to previous access control models, preferably the Congenial Access Control (CAC) model
Publication

10. Ogunseye, O. S., Adetiloye, P. K., Idowu, S. O., Folorunso, O., & Akinwale, A. T. (2011). Harvesting knowledge from computer-mediated social networks. Vine.

This paper aims to focus on how the advantages of computer mediated social networks (CMSN) can be effectively harnessed to create value for organizations in the form of ready knowledge and quick solutions to problems. Design/methodology/approach A knowledge capture technique – the Delphi technique – was fused into the social networking process. A model was designed to help show how this can be achieved and further illustrated through a case study of the dotCSC intranet portal – a social networking project conceptualized and designed by the authors for the Department of Computer Science, in the authors’ university. An online survey was carried out to determine the efficacy of the prototype dotCSC. Findings The results show that, though computer mediated social networks are regarded as major sources of social capital development and potential sources of knowledge capital, there is still room for improvement in their present design if they are to be effectively used for knowledge creation and management attaining their optimum potential. Conversely, the bad spells and pitfalls of KM acceptance and deployment in organizations tend to be reduced when it is amalgamated with SN. The survey conducted showed that the users of the dotCSC enjoyed using the prototype as they would any other CMSN and that the strategies employed in the development of the dotCSC was effective in problem solving, knowledge creation, capturing, and indeed, management. Research limitations/implications This improvement strategy is by no means exhaustive of the creative ways that knowledge capturing and management concepts can be combined and applied in the actual design of CMSNs for the benefit of organizations. It is meant to be an eye opener, a clarion call to developers and IS managers. It will also serve as a starting point into the future of objective KM oriented CMSN. Possible response bias from some respondents can be considered a primary limitation of the research. Originality/value Looking through existing documentation and literature would show that this research presents a novel approach/model in the design of CMSNs. It is able to aid knowledge generation or synthesis in organizations by objectively structuring staff conversations through the CMSNs to facilitate knowledge management. It can also help organizations leverage the success and appeal of CMSN in their design of KMSs.
Publication

11. Meta-heuristics based multi-layer access control technique (MBMAC). ANALE Seria Informatica, 145-154. WIth J. Okesola

Access control is a major preventative measure for sensitive resources. Most access control methods have been found to be inadequate in providing sufficient security to KMSs which house the sources of competitive advantage for many organizations today. However, current research showed that combining access control techniques can help provide better security. In this work, a meta-heuristic strategy for access control technique combination that is both more effective than previous methods of combination but also more effective is presented. The new method applies access control technique with human reasoning in a multilayer architecture ensuring that malicious users are prevented access and the misuse or abuse of priviledges common to other methods is stemmed.
Publication

12. Challenges in the adoption of visualization system: a survey
Kybernetes 2008. With Olusegun Folorunso

The need for maximum cognition from massive amounts of data is becoming explosive. Different visualization mechanisms are being introduced to achieve this aim. This paper aims to consider the state of organizations as regards being abreast with the recent visualization technologies. Design/methodology/approach – In this paper, the authors look critically at the system adoption life cycle as it applied to visualization system. Also, the two forms of visualization; static and dynamic are looked at, considering the least applied and why. An evaluation of the visualization system was implemented in order to discern if it provides any benefit to organizations. Findings – The study showed that the RT‐DANGO tool when compared to result from Excel exposed some spikes at some points when visualized dynamically which are not observed using usual static graph as it exposed some unseen events. The mean time taken to finish analysis of 4,000 concurrent‐related data were 168 s using RT‐DANGO and 121 s with the MS‐Excel. The difference was significant to p<0.05 (Z=−2.040). This was considered a reasonable tradeoff for accuracy, clarity and completeness of information. Originality/value – The paper shows the factors that are responsible for visualization's usage in organizations. The paper will thus serve as an eye opener to critical issues affecting the visualization industry to the benefit of all stakeholders. Some references are made to the challenges faced in Nigeria.
Publication

13. Folorunso, O., & Ogunseye, S. O. (2008). Applying an enhanced technology acceptance model to knowledge management in agricultural extension services. Data Science Journal, 7, 31-45

This research investigates the applicability of Davis’s Technology Acceptance Model (TAM) to agriculturist’s acceptance of a knowledge management system (KMS), developed by the authors. It is called AGROWIT. Although the authors used previous Technology Acceptance Model user acceptance research as a basis for investigation of user acceptance of AGROWIT, the model had to be extended and constructs from the Triandis model that were added increased the predictive results of the TAM, but only slightly. Relationships among primary TAM constructs used are in substantive agreement with those characteristic of previous TAM research. Significant positive relationships between perceived usefulness, ease of use, and system usage were consistent with previous TAM research. The observed mediating role of perceived usefulness in the relationship between ease of use and usage was also in consonance with earlier findings. The findings are significant because they suggest that the considerable body of previous TAM-related information technology research may be usefully applied to the knowledge management domain to promote further investigation of factors affecting the acceptance and usage of knowledge management information systems such as AGROWIT by farmers, extension workers, and agriculture researchers.
Publication

14. What’s to Learn from Unvalidated Sources of Health Information? In International Conference on Healthcare Informatics (ICHI), 2015 (pp. 593-596), IEEE. With Sherrie Komiak

Unvalidated Sources of Health Information (USHI) have been very successful in spite of the risk they pose to the health and well-being of their users. Our goal is to present a framework for the future study of USHI that studies the basic factors responsible for its success so as to enable the creation of better strategies to curb their use. Such studies leading to the identification of the components of USHI’s success can be useful in improving the design of other less adopted consumer healthcare systems. To achieve this goal, we suggest the “reverseengineering” of various information technology (IT) adoption and success theories to identify the actionable components of their antecedents with respect to USHI that can be directly useful to designers of IT artifacts. We also speculate on several potential benefits of such research beyond addressing the threat USHI represents.
Publication

15. The Impact of Senior-Friendliness Guidelines on Seniors’ Use of Personal Health Records, In International Conference on Healthcare Informatics (ICHI), (pp. 597-602). IEEE. With Sherrie and Paul Komiak

Usability is a key determinant of the adoption and use of Personal Health Record (PHR) by seniors. Usability principles exist to guide developers in the creation of senior friendly PHRs. The purpose of this study is to understand why seniors still perceive the usability of PHRs as low in spite of these publicly available guidelines. 16 PHRs were evaluated with a senior-focused website usability guideline to assess developers’ level of compliance. We found that though there are usability issues that need to be improved upon by PHR developers, some of the PHRs should be usable and senior-friendly. To understand the discrepancy between results of heuristic or guideline-based evaluation and reports from actual use, we contend that a need to assess existing usability standards for their suitability in guiding the creation of senior-friendly PHRs exists.
Publication

16. On the need for theory-grounded guidelines for designing senior-friendly personal health records. Proceedings of the Thirteenth Annual Workshop on HCI Research in MIS, Fort Worth, Texas, USA, December 13, 2015. With Sherrie and Paul Komiak

Personal Health Records (PHR) have the potential to improve healthcare access and quality while decreasing healthcare cost. However, the usability of PHRs is one of the major factors militating against adoption and sustained use by seniors. While senior-focused usability guidelines for websites exist, there are no usability guidelines for web-based senior-friendly PHRs. General senior-focused website usability guidelines do not cover enough of peculiarities of PHRsthat distinguishes it from normal websites like users’ input and interaction functions, health information security requirements, and seniors’ physiological needs. This paper, therefore, showcases the limitations of general website usability guidelines when they are applied in the PHR domain. To address this research gap, this paper aims to develop a new usability guideline for the development of senior-friendly PHRs. We do this in steps. First, a content analysis study is conducted on an online discussion forum on the perceptions of currently available PHRs. Second, a usability guideline for senior-friendly PHRs is developed based on Wixom and Todd’s Information Systems quality theory, the mental model theory and on the results of our content analysis in step 1. The new theory-grounded and practically suggested usability guideline has the potential to improve PHR design and adoption for seniors. An empirical study to test the proposed usability guideline is called for in future studies.
Publication

17. Folorunso, O., & Ogunseye, S. O. (2008). Applying an enhanced technology acceptance model to knowledge management in agricultural extension services. Data Science Journal, 7, 31-45.

This research investigates the applicability of Davis’s Technology Acceptance Model (TAM) to agriculturist’s acceptance of a knowledge management system (KMS), developed by the authors. It is called AGROWIT. Although the authors used previous Technology Acceptance Model user acceptance research as a basis for investigation of user acceptance of AGROWIT, the model had to be extended and constructs from the Triandis model that were added increased the predictive results of the TAM, but only slightly. Relationships among primary TAM constructs used are in substantive agreement with those characteristic of previous TAM research. Significant positive relationships between perceived usefulness, ease of use, and system usage were consistent with previous TAM research. The observed mediating role of perceived usefulness in the relationship between ease of use and usage was also in consonance with earlier findings. The findings are significant because they suggest that the considerable body of previous TAM-related information technology research may be usefully applied to the knowledge management domain to promote further investigation of factors affecting the acceptance and usage of knowledge management information systems such as AGROWIT by farmers, extension workers, and agriculture researchers.
Publication

18. Folorunso, O., Ogunseye, O. S., & Sharma, S. K. (2006). An exploratory study of the critical factors affecting the acceptability of e‐learning in Nigerian universities. Information management & computer security

Education delivery via electronic media is becoming relevant in Nigeria educational systems, especially the universities. In spite of this, there are hindrances affecting the total acceptability of this technology. Design/methodology/approach – In this paper, we investigated these critical factors by analyzing the questionnaires collected from three sampled universities in Nigeria: private, public and state owned universities. Findings – The results obtained indicated that mass unawareness, low computer literacy level and cost were identified as the critical factors affecting the acceptability of the technology. Originality/value – Analysis herein has shown the factors affecting the acceptability of e‐learning in Nigeria. The results obtained will assist policy makers by finding solutions to literacy problems in Nigeria.
Publication

19. Afolabi, D., Ogunseye, S., Sennaike, O., Adewole, P. Improving Decision Tree Classification with Ramen: A Ratio-Weighted Approach for Imbalanced Datasets. (2023).

Imbalanced datasets pose a common challenge in real-world applications, often leading to poor quality decision tree classifications. While previous approaches have attempted to tackle this problem, they have faced limitations such as overfitting and loss of useful datasets with significant negative impact on the quality of decisions made through such classifications. In our study, we introduce an optimized ratioweighted decision tree algorithm designed to address these limitations. Our algorithm takes a unique approach by retaining the minority instances present in the original dataset, avoiding the unnecessary discarding of potentially valuable data. By allowing the classification algorithm to determine the appropriate ratio of majority instances, we enhance the classification of minority samples. The results reveal that our proposed algorithm outperforms traditional decision tree classifiers and surpasses the minority entropy algorithm in identifying more members of the minority class. By effectively handling imbalanced data, our algorithm contributes to more reliable and precise decision-making processes.
Publication