Citizen science frontiers: Efficiency, engagement, and serendipitous discovery with human–machine systems

Trouille, Laura; Lintott, Chris; Fortson, L.

doi:10.1073/pnas.1807190116

Cited by 78 publications

(72 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moving the laboratory 'into the wild' 38 can overcome the excess of seclusion of controlled laboratory settings of much behavioural research. It is also in line with citizen science principles 39,40 which are increasingly encouraging the opening up of scientific research and practices to the general public [41][42][43][44][45][46][47][48][49] : from the research design, to the data collection, and the interpretation of the results.…”

mentioning

confidence: 52%

Gender-based pairings influence cooperative expectations and behaviours

Cigarini

Vicens

Perelló

2020

Sci Rep

View full text Add to dashboard Cite

The study explores the expectations and cooperative behaviours of men and women in a lab-in-thefield experiment by means of citizen science practices in the public space. It specifically examines the influence of gender-based pairings on the decisions to cooperate or defect in a framed and discrete Prisoner's Dilemma game after visual contact. Overall, we found that when gender is considered behavioural differences emerge in expectations of cooperation, cooperative behaviours, and their decision time depending on whom the partner is. Men pairs are the ones with the lowest expectations and cooperation rates. After visual contact women infer men's behaviour with the highest accuracy. Also, women take significantly more time to defect than to cooperate, compared to men. Finally, when the interacting partners have the opposite gender they expect significantly more cooperation and they achieve the best collective outcome. Together, the findings suggest that non verbal signals may influence men and women differently, offering novel interpretations to the context-dependence of gender differences in social decision tasks.

show abstract

mentioning

confidence: 52%

Gender-based pairings influence cooperative expectations and behaviours

Cigarini

Vicens

Perelló

2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Insect diversity is extraordinarily large – as an example, there are over 6,000 ladybird species worldwide (Roy & Brown, ), most of which do not have accessible labelled images. For difficult challenges, such as species identification in the field, the optimal solutions will involve humans and artificial intelligence working in tandem (Trouille, Lintott, & Fortson, ). Our results demonstrate the potential for considerable improvement in the accuracy of automatic identification when incorporating contextualization information directly within the model.…”

Section: Discussionmentioning

confidence: 99%

Thinking like a naturalist: Enhancing computer vision of citizen science images by harnessing contextual data

2020

View full text Add to dashboard Cite

1. The accurate identification of species in images submitted by citizen scientists is currently a bottleneck for many data uses. Machine learning tools offer the potential to provide rapid, objective and scalable species identification for the benefit of many aspects of ecological science. Currently, most approaches only make use of image pixel data for classification. However, an experienced naturalist would also use a wide variety of contextual information such as the location and date of recording.2. Here, we examine the automated identification of ladybird (Coccinellidae) records from the British Isles submitted to the UK Ladybird Survey, a volunteer-led mass participation recording scheme. Each image is associated with metadata; a date, location and recorder ID, which can be cross-referenced with other data sources to determine local weather at the time of recording, habitat types and the experience of the observer. We built multi-input neural network models that synthesize metadata and images to identify records to species level.3. We show that machine learning models can effectively harness contextual information to improve the interpretation of images. Against an image-only baseline of 48.2%, we observe a 9.1 percentage-point improvement in top-1 accuracy with a multi-input model compared to only a 3.6% increase when using an ensemble of image and metadata models. This suggests that contextual data are being used to interpret an image, beyond just providing a prior expectation. We show that our neural network models appear to be utilizing similar pieces of evidence as human naturalists to make identifications. 4. Metadata is a key tool for human naturalists. We show it can also be harnessed by computer vision systems. Contextualization offers considerable extra information, particularly for challenging species, even within small and relatively homogeneous areas such as the British Isles. Although complex relationships between disparate sources of information can be profitably interpreted by simple neural network architectures, there is likely considerable room for further progress. Contextualizing images has the potential to lead to a step change in the accuracy of automated S U PP O RTI N G I N FO R M ATI O NAdditional supporting information may be found online in the Supporting Information section.

show abstract

“…Insect diversity is extraordinarily large -as an example, there are over 6000 ladybird species 469 worldwide (Roy and Brown 2018), most of which do not have accessible labelled images. For difficult 470 challenges, such as species identification in the field, the optimal solutions will involve humans and 471 artificial intelligence working in tandem (Trouille, Lintott, & Fortson, 2019). Our results demonstrate 472 the potential for considerable improvement in the accuracy of automatic identification when 473 incorporating contextualisation information directly within the model.…”

Section: Conclusion 467mentioning

confidence: 91%

Thinking like a naturalist: enhancing computer vision of citizen science images by harnessing contextual data

Terry

Roy

August

2019

Preprint

View full text Add to dashboard Cite

The accurate identification of species in images submitted by citizen scientists is currently a bottleneck for many data uses. Machine learning tools offer the potential to provide rapid, objective and scalable species identification for the benefit of many aspects of ecological science. Currently, most approaches only make use of image pixel data for classification. However, an experienced naturalist would also use a wide variety of contextual information such as the location and date of recording. Here, we examine the automated identification of ladybird (Coccinellidae) records from the British Isles submitted to the UK Ladybird Survey, a volunteer‐led mass participation recording scheme. Each image is associated with metadata; a date, location and recorder ID, which can be cross‐referenced with other data sources to determine local weather at the time of recording, habitat types and the experience of the observer. We built multi‐input neural network models that synthesize metadata and images to identify records to species level. We show that machine learning models can effectively harness contextual information to improve the interpretation of images. Against an image‐only baseline of 48.2%, we observe a 9.1 percentage‐point improvement in top‐1 accuracy with a multi‐input model compared to only a 3.6% increase when using an ensemble of image and metadata models. This suggests that contextual data are being used to interpret an image, beyond just providing a prior expectation. We show that our neural network models appear to be utilizing similar pieces of evidence as human naturalists to make identifications. Metadata is a key tool for human naturalists. We show it can also be harnessed by computer vision systems. Contextualization offers considerable extra information, particularly for challenging species, even within small and relatively homogeneous areas such as the British Isles. Although complex relationships between disparate sources of information can be profitably interpreted by simple neural network architectures, there is likely considerable room for further progress. Contextualizing images has the potential to lead to a step change in the accuracy of automated identification tools, with considerable benefits for large‐scale verification of submitted records.

show abstract

Citizen science frontiers: Efficiency, engagement, and serendipitous discovery with human–machine systems

Cited by 78 publications

References 60 publications

Gender-based pairings influence cooperative expectations and behaviours

Gender-based pairings influence cooperative expectations and behaviours

Thinking like a naturalist: Enhancing computer vision of citizen science images by harnessing contextual data

Thinking like a naturalist: enhancing computer vision of citizen science images by harnessing contextual data

Contact Info

Product

Resources

About