The second stream within the NESP 5.5 project was conducted using eye-tracking technology to examine possible differences between three participant groups in evaluating the aesthetic beauty of GBR underwater sceneries. This research continue the efforts initiated in the previous NESP 3.2.3 project to explore the power of eye-tracking as an objective measure of human aesthetic assessment of GBR underwater sceneries. By employing a sample of three social-cultural groups (non-indigenous Australians, Chinese and First Peoples), this research provides further empirical evidence for the effectiveness of eye-tracking in aesthetic research in a cross-cultural context. Data collected using eye tracking was stored in one Excel file of eye-tracking data exported from Tobii eye-tracking device and 20 heatmaps showing participants’ visual attention to 20 images of underwater GBR sceneries. Methods: Following the initial research conducted in the previous NESP 3.2.3 project, 93 participants of various socio-cultural backgrounds (non-indigenous Australians, First People Australians and Chinese) were recruited using convenience sampling in this study. Participants were asked to sit in front of a screen-based eye-tracking equipment (i.e. Tobii T60 eye-tracker) after providing informed consent. Participants were free to look at each picture on screen as long as they wanted during which their eye movements were recorded (similar to lab setting in NESP 3.2.3). They also rated each picture on a 10-point beauty scale (1-Not beautiful at all, 10-Very beautiful). Raw eye-tracking data was then imported to IBM SPSS using SAV. format for data analysis. Raw eye-tracking data was then extracted from Tobii eye-tracking device (i.e. picture beauty, time to first fixation, fixation count, fixation duration and total visit time) in Exel format. Twenty heatmaps in Png format generated from the eye-tracking software to show participants’ visual attention were also included. As an extension of the previous study conducted within the NESP 3.2.3 project, data collected was used to examine the influences of social-cultural differences in aesthetic assessment of GBR underwater sceneries. Advanced technologies were used in combination with self-reporting measurements for a better understanding of socio-cultural differences and socio-cultural influences on aesthetic assessment among three groups. Eye-tracking provides a measure of visual attention, enabling researchers to explore further potential differences among three groups regarding their interest in viewing and assessing the GBR aesthetics. Previous research (NESP 3.2.3) demonstrated that eye-tracking measures of viewers' visual attention (i.e., fixation duration and fixation count) and aesthetic ratings are correlated, suggesting the usefulness of eye-tracking in aesthetic research. This study verifies the usefulness of eye-tracking in aesthetic research in a cross-cultural context. Participants were exposed to 20 images of underwater GBR scenery in random order which were used in the previous focus groups. Further information can be found in the following publication: Le, D., Becken, S., & Whitford, M. (2020) A cross-cultural investigation of the great barrier Reef aesthetics using eye-tracking and face-reader technologies. Report to the National Environmental Science Program. Reef and Rainforest Research Centre Limited, Cairns. Published online at https://nesptropical.edu.au/wp-content/uploads/2020/09/NESP-TWQ-Project-5.5-Technical-Report-2.pdf Format: The eye-tracking folder contains one Excel file containing raw eye-tracking data and 20 heatmaps generated from eye-tracking software in Png format. Data Dictionary: - Beauty1: Name of the corresponding GBR underwater picture used in the eye-tracking experiment - ABeauty1: Aesthetic evaluations of the corresponding picture (e.g., Beauty1) - EBeauty1: Aesthetic emotion (i.e., pleasant) of the corresponding picture (e.g., Beauty1) - FD_Beauty1: Fixation duration in the picture Beauty1 (i.e. the average length of all fixations during all recordings in the whole picture). A longer fixation means that the object is more engaging in some way. Measurement unit: - AOIFD_Beauty1: Fixation duration in the central area of interest (AOI) in picture Beauty1 (i.e. the average length of all fixations during all recordings in the whole picture). A longer fixation means that the object is more engaging in some way. - FC_Beauty1: Fixation count in the picture Beauty1 (i.e. the average number of fixations in the picture). - AOIFC_Beauty1: Fixation count in the central area of interest (AOI) in picture Beauty1 (i.e. the average number of fixations in the picture). Similar labels are used for other pictures, including Beauty 2,3,4; Human 1,3,5,6; Medium 1,2,3,4; Restoration 1,2,3,8 and Ugly 1,2,3,4. Further information can be found in the following publication: Le, D., Becken, S., & Whitford, M. (2020) A cross-cultural investigation of the great barrier Reef aesthetics using eye-tracking and face-reader technologies. Report to the National Environmental Science Program. Reef and Rainforest Research Centre Limited, Cairns. Published online at https://nesptropical.edu.au/wp-content/uploads/2020/09/NESP-TWQ-Project-5.5-Technical-Report-2.pdf References: Murray, N., Marchesotti, M. & Perronnin, F (2012). AVA: A Large-Scale Database for Aesthetic Visual Analysis. Available (09/10/17) http://refbase.cvc.uab.es/files/MMP2012a.pdf Data Location: This dataset is filed in the eAtlas enduring data repository at: data\custodian\2019-2022-NESP-TWQ-5\5.5_Measuring-aesthetics

The last stream within the NESP 5.5 project was related to the conduct of an online survey to get aesthetic ratings of additional 3500 images downloaded from Flickr to improve the Artificial Intelligence (AI)-based system recognising and assessing the beauty of natural scenes, which had been developed in the previous NESP 3.2.3 project. Despite some earlier investment into this research area, there is still a need to improve the tools we use to measure the aesthetic beauty of marine landscapes. This research drew on images publicly available on the Internet (in particular through the photo sharing site Flickr) to build a large dataset of GBR images for the assessment of aesthetic value. Building on earlier work in NESP TWQ Hub Project 3.2.3, we conducted a survey focused on collecting beauty scores of an additional large number of GBR images (n = 3500). This dataset consists of one dataset report, two word files and one excel file demonstrating the aesthetic ratings collected used to improve the accuracy of the aesthetic monitoring AI system. Methods: The third research stream was conducted on the basis of an online survey to collect aesthetic ratings of 1585 Australians to rate the aesthetic beauty of 3500 GBR underwater pictures downloaded and selected from Flickr. Flickr is an image hosting service and one of the main sources of images for our project. As per our requirement, we downloaded all images and their metadata (including coordinates where available) based on keyword filter such as “Great Barrier Reef”. The Flickr API is available for non-commercial (but commercial use is possible by prior arrangement) use by outside developers. To ensure a much larger and diverse supply of photographs, we have developed a python-based application using Flickr API that allowed us to download Flickr images by keyword (e.g. “Great Barrier Reef” available at https://www.flickr.com). The focus of this research was on under-water images, which had to be filtered from the downloaded Flickr photos. From the collected images we identified an additional number of 3020 relevant images with coral and fish contents out of a total of approximately 55,000 downloaded images. Matt Curnock, CSIRO expert, also provide 100 images from his private images taken at the GBR and consent to use these images for our research. In total, 3120 images were selected and renamed to be rated in a survey by Australian participants (see two file “Image modification” and “Matt image rename” in the AI folder for further details). The survey was created on Qualtrics website and launched in in April 2020 using Qualtrics survey service. After giving the consent to participating in the online survey, each respondent was randomly exposed to 50 images of the GBR and rate the aesthetic of the GBR scenery on a 10 point scale (1-Very ugly/unpleasant – Very beautiful/pleasant). In total, 1585 complete and valid questionnaires were recorded. Aesthetic rating results was exported to an Excel file and used for improving the accuracy of the computer algorithm recognising and assessing the beauty of natural scenes which had been developed in the previous NESP 3.2.3 project. Further information can be found here: Stantic, B. and Mandal, R. (2020) Aesthetic Assessment of the Great Barrier Reef using Deep Learning. Report to the National Environmental Science Program. Reef and Rainforest Research Centre Limited, Cairns (30pp.). Available at https://nesptropical.edu.au/wp-content/uploads/2020/11/NESP-TWQ-Project-5.5-Technical-Report-3.pdf Format: The AI DATASET has one dataset report, one excel file showing aesthetic ratings of all images and two Word files showing how images downloaded from Flickr website and provided by Matt Curnock (CSIRO) were renamed and used for aesthetic ratings and AI development. The aesthetic rating results were later used to improve the accuracy of the AI aesthetic monitoring system for the GBR. Further information can be found here: Stantic, B. and Mandal, R. (2020) Aesthetic Assessment of the Great Barrier Reef using Deep Learning. Report to the National Environmental Science Program. Reef and Rainforest Research Centre Limited, Cairns (30pp.). Available at https://nesptropical.edu.au/wp-content/uploads/2020/11/NESP-TWQ-Project-5.5-Technical-Report-3.pdf References: Murray, N., Marchesotti, M. & Perronnin, F (2012). AVA: A Large-Scale Database for Aesthetic Visual Analysis. Available (09/10/17) http://refbase.cvc.uab.es/files/MMP2012a.pdf Data Location: This dataset is filed in the eAtlas enduring data repository at: data\custodian\2019-2022-NESP-TWQ-5\5.5_Measuring-aesthetics

Organizing focus groups was used as an effective qualitative research method to examine collective opinions of participants on a specific topic. Within NESP 5.5 project, focus groups consist of an exploratory study to explore the psychological antecedents of human aesthetic assessment of underwater sceneries at the GBR among three groups of different cultural backgrounds: Chinese, non-indigenous Australians and First People Australians. Focus group folder contains one dataset report, and three folders (Australian, Chinese, First People) with seven images. Methods: Within the NESP 5.5 project, 29 respondents were recruited in four focus groups: 1) Focus group with 7 non-Indigenous Australian citizen respondents: 2nd May 2019 2) Focus group with 8 Chinese visitor respondents: 7th May 2019 3) 1st focus group with 5 First Peoples respondents: 31st May 2019 4) 2nd focus group with 9 First Peoples respondents: 5th June 2019 During each focus group, respondents were asked to share their top-of-mind and personal experiences with the GBR. Next, they worked together to rank 20 underwater images of the GBR from what they thought to be the most beautiful, to the least beautiful scenery in two rounds (10 images/round). These 20 images represent five environmental conditions of the GBR (highly aesthetic, medium aesthetic, low aesthetic, polluted areas with the presence of some rubbish and coral restoration sites). These were selected based on aesthetic ratings in project NESP TWQ 3.2.3 and an agreement among the research team of eight experts. With the approval of all participants, each focus group was audio-recorded and later transcribed using REV Ltd.’s transcribing services. For more information about the audio recordings please contact: Dr (Jenny) Dung Le (email: dung.ltp@vinuni.edu.vn) Further information can be found in the following publication: Le, D., Becken, S., & Whitford, M. (2020) A cross-cultural investigation of the great barrier Reef aesthetics using eye-tracking and face-reader technologies. Report to the National Environmental Science Program. Reef and Rainforest Research Centre Limited, Cairns. Published online at https://nesptropical.edu.au/wp-content/uploads/2020/09/NESP-TWQ-Project-5.5-Technical-Report-2.pdf Format: The focus group folder includes one dataset report form and three subfolders labelled Australians, Chinese and First People. Each subfolder contains images in Png format showing picture rankings during these focus groups. Data Dictionary: - FG: Focus Group - Australian FG1/2: Picture 1/2 taken in the focus group discussion with non-indigenous Australian participants. - Chinese FG1/2: Picture 1/2 taken in the focus group discussion with Chinese participants. - First People FG1: Picture taken in the first focus group discussion with First People participants. - First People FG1.R1/2: Picture 1/2 taken in the second focus group discussion with First People participants. References: Data Location: This dataset is filed in the eAtlas enduring data repository at: data\custodian\2019-2022-NESP-TWQ-5\5.5_Measuring-aesthetics

This dataset resulted from two inter-linked research streams. The first stream was related to the application of eye-tracking technology and an online survey in studying natural beauty. The second stream is related to the development of an Artificial Intelligence (AI)-based system recognising and assessing the beauty of natural scenes. Due to differences in data collection and data analysis, details of research methods used for each research stream are described in three separated data records. This record that describes the common elements and goals of the three parts to the research. Within these research streams, three datasets were developed. These include: Eye tracking - containing the outcome documents of eye-tracking experiment conducted within the project framework Online survey - includes a survey format document and three subfolders showing how each section of the survey was designed and outcome of each section (i.e. conjoint analysis, picture rating and open question) Algorithm data reflecting how a computer-based system for automated assessment of image attractiveness is developed Format and methods: The project dataset has multiple parts containing data of different formats and methods. Details of each dataset are discussed in the corresponding data records. Data Dictionary: See data dictionaries in the following data report forms: Becken, S., Connolly R., Stantic B., Scott N., Mandal R., Le D., (2018), Eye-tracking data report form, Griffith Institute for Tourism Research Report No 15. Becken, S., Connolly R., Stantic B., Scott N., Mandal R., Le D., (2018), Online survey data report form, Griffith Institute for Tourism Research Report No 15. Becken, S., Connolly R., Stantic B., Scott N., Mandal R., Le D., (2018), Algorithm data report form, Griffith Institute for Tourism Research Report No 15. References: Further information can be found in the following publication: Becken, S., Connolly R., Stantic B., Scott N., Mandal R., Le D., (2018), Monitoring aesthetic value of the Great Barrier Reef by using innovative technologies and artificial intelligence, Griffith Institute for Tourism Research Report No 15. Becken, S., Connolly R., Stantic B., Scott N., Mandal R., Le D., (2018), Eye-tracking data report form, Griffith Institute for Tourism Research Report No 15. Becken, S., Connolly R., Stantic B., Scott N., Mandal R., Le D., (2018), Online survey data report form, Griffith Institute for Tourism Research Report No 15. Becken, S., Connolly R., Stantic B., Scott N., Mandal R., Le D., (2018), Algorithm data report form, Griffith Institute for Tourism Research Report No 15. Data Location: This dataset is filed in the eAtlas enduring data repository at: data\nesp3\3.2.3_Aesthetic-Values-GBR

This dataset contains the caffe deep-learning framework along with the setup for image aesthetic train and test code for the Algorithm data. We used NVIDIA-digit 6 environment and this version use caffe 0.15.14 More details information can be found in http://caffe.berkeleyvision.org. This dataset consists of two folders which are related to automatic aesthetic rating of images using Deep Learning. . GBR-Aesthetics-Data: This folder contains few sub folders. 1. data-images: - 2500 images used to survey the score. - 2500 images after resize to 224x224 pixels - imagenet mean file - a file essential for neural network training - train list files - list of file names used for training - test list files – list of file names used for testing 2. lmdb : Two sets of converted images and score into lmdb format. Lmdb format is required during train and test process. 3. tar.gz : tar file contains model definition, trained models and information related to configuration (solver) parameters 4. Qualtrics.xls file contains files names along with their surveyed scores. 5. Infer Many Images.html – Contains generated score from 500 test images using our deep learning model. GBR-Aesthetics-code: It contains a caffe deep learning framework code. Methods: The following step were used to prepare the dataset: 1. Flickr API was used to download more than 10,000 images using a keyword “Great Barrier Reef”. About 10,000 pictures were downloaded in August and September 2017. 2. 2500 images were manually selected to conduct an online survey for manual score assessment based on several research criteria: (i) underwater pictures of GBR, (ii) without humans, (iii) viewed from 1-2 metres from objects and (iv) of high resolution. 3. The survey was created on Qualtrics website and launched on 4th October 2017 using Qualtrics survey service. 772 survey completions were recorded and 705 questionnaires were eligible for data analysis after filtering unqualified questionnaires. 4. At least 10 participants were used to score one picture in a range of 1 to 10. An average score was considered as an actual score. 5. The GBR-aesthetic-code folder actually contains the caffe deep-learning framework along with the setup for image aesthetic train and test code. More details information can be found in http://caffe.berkeleyvision.org. We used NVIDIA-digit 6 environment and this version use caffe 0.15.14 Format: 1. All image files are stored as JPEG (.jpg format) – This images are used for training and testing. However, files are converted to lmdb format before used for actual training process. 2. All deep learning configuration files are saved as recommended prototxt files. 3. lmdb format is used to prepare the final training sets. 4. training and test file lists are stored in txt files. 5. surveyed information are stored in xls files. 6. train_val.prototxt file describes the network definition used for training. 7. solver.protxt contains information related to network configuration parameters 8. snapshot_iter_3360.caffemodel- It is a trained model after 3360 iterations 9. deploy.prototxt- contains network definition of test process. Data Location: This dataset is filed in the eAtlas enduring data repository at: data\nesp3\3.2.3_Aesthetic-value-GBR