On the Effectiveness of Crowd Sourcing Avian Nesting Video Analysis at Wildlife@Home

Desell, Travis; Goehner, Kyle; Andes, Alicia K.; Eckroad, Rebecca; Ellis‐Felege, Susan N.

doi:10.1016/j.procs.2015.05.258

Cited by 9 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While this should be explored with a larger sample of the general population, the popularity of citizen science sites such as Zooniverse.org and Dognition.com suggest that it is possible to recruit large numbers of people for such studies and therefore that our method is repeatable. We suggest it is likely that there is a general willingness to participate in such behavioural research and that it can engage the public interest, as for other crowd sourced science projects (Desell et al 2015;Law et al 2017). As our participants were mostly undergraduate psychology students, there may have been a bias towards participants who were potentially more painstaking than average in their responses as they were being rewarded with course credit.…”

Section: Discussionmentioning

confidence: 99%

“…This has produced large-scale datasets which could not otherwise be generated (e.g. surveying bird species distributions at national or international levels by using local reports by ornithologists) (Desell et al 2015 ). More recently with the expansion of the internet, researchers have adopted crowdsourcing approaches for mass data analysis tasks which are time-consuming or cannot be automated easily (Cox et al 2015 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using a new video rating tool to crowd-source analysis of behavioural reaction to stimuli

et al. 2021

View full text Add to dashboard Cite

Quantifying the intensity of animals’ reaction to stimuli is notoriously difficult as classic unidimensional measures of responses such as latency or duration of looking can fail to capture the overall strength of behavioural responses. More holistic rating can be useful but have the inherent risks of subjective bias and lack of repeatability. Here, we explored whether crowdsourcing could be used to efficiently and reliably overcome these potential flaws. A total of 396 participants watched online videos of dogs reacting to auditory stimuli and provided 23,248 ratings of the strength of the dogs’ responses from zero (default) to 100 using an online survey form. We found that raters achieved very high inter-rater reliability across multiple datasets (although their responses were affected by their sex, age, and attitude towards animals) and that as few as 10 raters could be used to achieve a reliable result. A linear mixed model applied to PCA components of behaviours discovered that the dogs’ facial expressions and head orientation influenced the strength of behaviour ratings the most. Further linear mixed models showed that that strength of behaviour ratings was moderately correlated to the duration of dogs’ reactions but not to dogs’ reaction latency (from the stimulus onset). This suggests that observers’ ratings captured consistent dimensions of animals’ responses that are not fully represented by more classic unidimensional metrics. Finally, we report that overall participants strongly enjoyed the experience. Thus, we suggest that using crowdsourcing can offer a useful, repeatable tool to assess behavioural intensity in experimental or observational studies where unidimensional coding may miss nuance, or where coding multiple dimensions may be too time-consuming.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Using a new video rating tool to crowd-source analysis of behavioural reaction to stimuli

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Their involvement in monitoring is already established through the many Citizen Science projects where citizens provide data (17) or analyze environmental data (24). It is easy to imagine how automated monitoring systems create micro-tasks that will be evaluated by humans, for example, to inspect photos for the early detection of plant stress, or count the number of pollinators that visit a flower in a video to produce an indicator of biodiversity (25).…”

Section: Human Computation and Adaptive Managementmentioning

confidence: 99%

Agroecology: A Fertile Field for Human Computation

Hanappe

Dunlop

Maes³

et al. 2016

HCj

View full text Add to dashboard Cite

Agroecology -the science of sustainable agriculture -offers a new and positive perspective for the creation of sustainable food systems. We argue that, from the outset, it is important to involve citizens in this development to create the necessary, bottom-up support for change in agriculture and to re-establish the ties between food production and consumption. Human Computation and Citizen Science offer opportunities to include citizens in the planning, monitoring and evaluation of agro-ecosystems. In the P2P Food Lab project, we also seek new ways to engage them more creatively by setting up a shared online/offline platform in which they can learn, practice, innovate, and share observations on agroecological techniques. In this Brief we give a descriptive account of our ongoing work on this agroecology and HCI application.

show abstract

“…To the best of our knowledge, this is the first attempt at building image classification models to help identify the trade of exotic live animals on the internet. This work differs from other image identification studies in conservation science (e.g., [15]; [16]; [17]; [18] [19]; [20]; [21]), in its application in the wildlife trade context and ability to deduce the context of the target object. The objective here is not to detect a pattern that identifies the animal, but rather to deduce if an animal is present in the image along with identifying the context (e.g., a cage) in which the animal is present.…”

Section: Introductionmentioning

confidence: 98%

Towards automatic detection of wildlife trade using machine vision models

Kulkarni¹,

Minin²

2022

Preprint

View full text Add to dashboard Cite

Unsustainable trade in wildlife is one of the major threats affecting the global biodiversity crisis. An important part of the trade now occurs on the internet, especially on digital marketplaces and social media. Automated methods to identify trade posts are needed as resources for conservation are limited. Here, we developed machine vision models based on Deep Neural Networks with the aim to automatically identify images of exotic pet animals for sale. A new training dataset representing exotic pet animals advertised for sale on the web was generated for this purpose. We trained 24 neural-net models spanning a combination of five different architectures, three methods of training and two types of datasets. Specifically, model generalisation improved after setting a portion of the training images to represent negative features. Models were evaluated on both within and out of distribution data to test wider model applicability. The top performing models achieved an f-score of over 0.95 on within distribution evaluation and between 0.75 to 0.87 on the two out of distribution datasets. Notably, feature visualisation indicated that models performed well in detecting the surrounding context (e.g. a cage) in which an animal was located, therefore helping to automatically detect images of animals in non-natural environments. The proposed methods can help investigate the online wildlife trade, but can also be adapted to study other types of people-nature interactions from digital platforms. Future studies can use these findings to build robust machine learning models and new data collection pipelines for more taxonomic groups.

show abstract

On the Effectiveness of Crowd Sourcing Avian Nesting Video Analysis at Wildlife@Home

Cited by 9 publications

References 9 publications

Using a new video rating tool to crowd-source analysis of behavioural reaction to stimuli

Using a new video rating tool to crowd-source analysis of behavioural reaction to stimuli

Agroecology: A Fertile Field for Human Computation

Towards automatic detection of wildlife trade using machine vision models

Contact Info

Product

Resources

About