User Acceptance of IBON (Image-Based Ornithological Identification) Monitoring in a Mobile Platform: A TAM-Based Study ^†

Abstract

This study investigates user acceptance of the IBON Monitoring system, a mobile app that uses image recognition to identify bird species. Using the Technology Acceptance Model (TAM), it surveyed 100 faculty and students at Romblon State University to assess factors like perceived usefulness, ease of use, computer literacy, and self-efficacy. Results showed that usefulness and ease of use significantly influence user attitudes and intentions. The findings suggest actionable recommendations for improving IBON system adoption, including training programs to enhance computer literacy and self-efficacy and strategies to demonstrate the system’s relevance to user needs. Future research should explore additional external factors, such as cultural influences and user experience design, and conduct longitudinal studies to assess sustained use and impact on biodiversity monitoring outcomes. This study underscores the importance of fostering user acceptance to maximize the potential of innovative technologies like IBON Monitoring in advancing biodiversity conservation efforts.

1. Introduction

The conservation of biodiversity is increasingly recognized as a critical global concern, necessitating innovative solutions to address environmental challenges. Birds serve as vital indicators of ecological health due to their sensitivity to habitat changes and their roles in maintaining ecosystem balance [1]. Effective monitoring of bird populations is essential for conservation efforts; however, traditional methods such as manual observation and point counts are often resource-intensive, time-consuming, and susceptible to human error [2]. This underscores the urgent need for technological advancements that can streamline biodiversity monitoring processes and enhance data accuracy. Recent innovations, particularly in mobile platforms and artificial intelligence (AI)-based tools, have transformed ecological monitoring. Image-based identification systems and GPS-enabled applications have shown promise in automating species detection, minimizing human error, and facilitating real-time data collection [3]. Applications like Merlin Bird ID and iNaturalist exemplify how mobile platforms empower users to contribute to scientific data gathering while fostering public engagement in conservation efforts [4]. Nevertheless, these tools face challenges regarding user adoption, especially in developing countries where access to technology and digital literacy can vary significantly [2]. The Philippines, recognized for its rich avifauna within the East Asian–Australasian Flyway, presents an ideal context for exploring the application of such technologies. Despite the country’s diverse migratory and endemic bird species, monitoring efforts are often hampered by limited resources and accessibility challenges [1]. To address these issues, the IBON (Image-Based Ornithological IdeNtification) Monitoring System was developed as a mobile platform that integrates image recognition and geolocation capabilities to simplify bird identification and monitoring. The system aims to empower users—students and faculty alike—to contribute to avian biodiversity data collection through a user-friendly interface. To assess the potential adoption of IBON, this study employs the Technology Acceptance Model (TAM), which identifies perceived usefulness (PU) and perceived ease of use (PEOU) as primary factors influencing a user’s intention to adopt new technologies [2]. By incorporating external variables such as gender, designation (faculty or student), and technological self-efficacy, this research seeks to provide a comprehensive understanding of the factors affecting user acceptance of the IBON Monitoring System. This study aims to fill a critical gap in the literature by examining user acceptance of mobile biodiversity monitoring systems within the Philippine context. By analyzing the interplay between TAM constructs and external variables, the research contributes valuable insights into designing user-centered ecological monitoring tools. Ultimately, this study aspires to support broader conservation efforts by facilitating the adoption of innovative technologies that enable more effective and inclusive biodiversity management practices [3,4].

2. The Related Literature

2.1. Biodiversity Monitoring Challenges

Accurate biodiversity monitoring plays a pivotal role in evaluating ecosystem health and informing conservation strategies. Despite its importance, traditional monitoring methods, such as manual observations and the use of lower-end cameras, are often resource-intensive, time-consuming, and susceptible to human error [5]. These limitations hinder the capacity to effectively track and analyze species distribution and abundance [6]. To address these challenges, automated systems such as acoustic sensors and image recognition algorithms have been developed. These technologies offer significant improvements in efficiency and accuracy by automating species detection and identification processes [7,8]. However, the detection of cryptic or rare species remains a significant challenge, as these technologies can be constrained by environmental noise, limited training datasets, and the variability of species appearances [9].

2.2. Mobile Platforms in Conservation

Mobile platforms have emerged as transformative tools in biodiversity conservation, enabling real-time data collection and analysis. Applications like eBird and Merlin Bird ID empower citizen scientists and researchers to identify and record species with minimal expertise [10]. These tools often integrate advanced features such as geotagging, machine learning, and offline functionality, making them suitable for use in remote or resource-limited areas [10,11,12,13,14,15,16,17,18]. However, their adoption is influenced by factors such as accessibility, usability, and the availability of user-friendly interfaces [6]. Moreover, integrating these tools into conservation practices requires an understanding of the user experience, particularly in the context of developing nations where barriers such as digital literacy and limited smartphone penetration persist [11].

2.3. Technology Acceptance Model

The Technology Acceptance Model (TAM) (Figure 1), first proposed by Davis (1989) [12], provides a robust framework for understanding user adoption of new technologies. Central to the model are two constructs: perceived ease of use (PEOU), referring to the effort required to use the system, and perceived usefulness (PU), reflecting the system’s contribution to task performance (Davis and Venkatesh, 1996) [13]. These factors influence user attitudes, which in turn shape behavioral intentions and actual usage of technology. TAM has been extended over the years to include external variables such as demographic factors, user expertise, and situational influences.

2.4. TAM in the Context of IBON Monitoring

In this study, TAM serves as a foundational framework to examine the acceptance of the IBON (Image-Based Ornithological IdeNtification) Monitoring System. While PU and PEOU remain central to the analysis, the model is extended to incorporate external variables including sex and user designation (faculty or student) [2]. These variables are hypothesized to influence user perceptions of ease of use and usefulness, thereby affecting attitudes and behavioral intentions toward adopting the platform. By integrating TAM with user demographic factors, this research aims to provide a comprehensive understanding of how different groups interact with the IBON system in a Philippine context.

3. Materials and Methods

3.1. Survey Instrument and Constructs

The survey instrument was based on constructs validated by the comparative study of Davis et al. (1989) [12] and adapted to the context of this research. The questionnaire items, as illustrated in

Table 1. Variables and number of items.

Variables	Number of Items
Perceived Usefulness	4
Perceived Ease of Use	4
Attitude Toward Using	4
Behavioral Intention	4
Actual Use	-

, were designed to measure responses on a 5-point Likert scale, ranging from “Strongly Disagree” to “Strongly Agree”.

Based on these constructs, the following hypotheses were formulated:

Hypothesis 1 (H1). 

PU positively influences BI.

Hypothesis 2 (H2). 

PEOU positively influences BI.

Hypothesis 3 (H3). 

PEOU positively influences PU.

Hypothesis 4 (H4). 

PU positively influences visibility.

Hypothesis 5 (H5). 

PU positively influences domain knowledge.

Hypothesis 6 (H6). 

Self-efficacy positively influences PEOU.

Hypothesis 7 (H7). 

Computer literacy positively influences PEOU.

3.2. Predictors and Hypotheses

The study explored key variables under the Technology Acceptance Model (TAM) framework, focusing on perceived usefulness (PU), perceived ease of use (PEOU), attitude toward using (ATU), behavioral intention (BI), and actual use (AU). Table 1 outlines the variables and the number of items used in the study.

3.3. Factors Used in the Model

• Perceived usefulness (PU): The degree to which users believe the system enhances their performance [14];
• Perceived ease of use (PEOU): The extent to which the system is easy to operate [15];
• Behavioral intention (BI): The motivational factors influencing system usage, with greater intent leading to a higher likelihood of adoption [16].

3.4. External Factors Predicting PU and PEOU

• Domain knowledge (DK): Defined as a user’s familiarity with relevant information, enabling effective interaction with systems [14];
• Relevance: The extent to which system outputs align with user needs, grounded in their practical application [17];
• Computer literacy (CL): Basic proficiency in computer usage to facilitate efficient system interaction [14];
• Self-efficacy (SE): A user’s confidence in their ability to use systems effectively [16].

3.5. Participants

The survey was conducted among 100 respondents from Romblon State University, comprising both students and faculty members, as shown in

Table 2. Profile of respondents.

Background Information		Frequency	%
Sex	Male	46	46%
	Female	54	54%
Designation	Faculty	60	60%
	Student	40	40%

. The demographic breakdown ensured balanced representation.

4. Results and Findings

4.1. Descriptive Statistics

The descriptive statistics presented in

Table 3. Descriptive statistics.

Item	Construct	Min	Max	Mean	Std. Deviation
PU1	Perceived Usefulness	3	5	4.64	0.578
PU2		3	5	4.67	0.514
PU3		3	5	4.69	0.526
PU4		3	5	4.56	0.574
PEU1	Perceived Ease of Use	3	5	4.43	0.555
PEU2		3	5	4.40	0.569
PEU3		3	5	4.45	0.557
PEU4		3	5	4.46	0.610
ATU1	Attitude Toward Using	3	5	4.50	0.644
IU1	Behavioral Intention	3	5	4.44	0.641

summarize the variables used in the study. Responses ranged from neutral (3) to strongly agree (5), with mean scores indicating favorable attitudes toward the system across all constructs.

4.2. Reliability Analysis

Cronbach’s alpha was calculated to evaluate the internal consistency of the survey instrument. As shown in

Table 4. Cronbach’s alpha.

Variables	Cronbach’s Alpha	No. of Items
Perceived Usefulness	0.91	4
Perceived Ease of Use	0.96	4
Attitude Toward Using	0.90	4
Behavioral Intention	0.92	4

, all variables scored above 0.90, indicating excellent reliability.

4.3. Correlation Analysis

The correlation matrix presented in

Table 5. Correlation matrix.

	PU	PEU	ATU	IU
PU	1
PEU	0.705 **	1
ATU	0.757 **	0.832 **	1
IU	0.748 **	0.813 **	0.886 **	1

Note: ** Correlation is significant at the 0.01 level (2-tailed).

illustrates the relationships between constructs. All constructs exhibit statistically significant correlations, as the p-values are below the 0.01 significance level.

The results affirm that PU, PEOU, ATU, and BI are strongly interrelated, reinforcing the validity of the TAM framework in this context.

5. Conclusions

This study explored the factors influencing user acceptance of the IBON Monitoring system through the Technology Acceptance Model (TAM). The findings reveal that perceived usefulness (PU) and perceived ease of use (PEOU) are critical determinants of users’ attitudes and behavioral intentions toward adopting the system. Users who view the IBON Monitoring system as beneficial and easy to use are more likely to develop favorable attitudes and a strong intention to engage with the platform. External factors such as computer literacy and self-efficacy significantly contribute to PEOU, while domain knowledge and relevance enhance PU. These findings affirm the extended TAM framework’s applicability in biodiversity monitoring. The study also highlights demographic differences, with faculty and students exhibiting distinct acceptance dynamics. This underscores the importance of tailored implementation strategies and training programs to maximize adoption rates among diverse user groups. The reliability and correlation analyses validate the robustness of the survey instrument and underscore the interrelationships among TAM constructs. These results reinforce TAM’s predictive power in innovative applications like IBON Monitoring, demonstrating its utility in assessing technology acceptance within conservation contexts. To foster broader adoption of the IBON Monitoring system, developers and policymakers should focus on addressing user perceptions. Training programs that enhance computer literacy and self-efficacy can empower users, particularly in resource-limited settings. Clear demonstrations of the system’s alignment with user needs will improve its perceived relevance and utility. Future research should investigate additional external factors, such as cultural influences and user experience design, to further refine TAM’s predictive capabilities. Longitudinal studies could evaluate sustained system use and its impact on biodiversity monitoring outcomes, providing insights into the long-term effectiveness of technology-driven conservation efforts. In conclusion, the IBON Monitoring system has significant potential to advance biodiversity conservation initiatives. By addressing user perceptions of usefulness and ease of use while considering demographic and contextual factors, stakeholders can ensure the system’s successful implementation. Fostering user acceptance is essential for leveraging technology to improve data collection and contribute meaningfully to global conservation efforts.