Widespread concern over declines in pollinating insects has led to numerous recommendations of which "pollinator-friendly" plants to grow and help turn urban environments into valuable habitat for such important wildlife. Whilst communicated widely by organisations and readily taken up by gardeners, the provenance, accuracy, specificity and timeliness of such recommendations remain unclear. Here we use data (6429 records) gathered through a UK-wide citizen science programme (BeeWatch) to determine food plant use by the nation's bumblebee species, and show that much of the plant use recorded does not reflect practitioner recommendations: correlation between the practitioners' bumblebee-friendly plant list (376 plants compiled from 14 different sources) and BeeWatch records (334 plants) was low (r = 0.57), and only marginally higher than the correlation between BeeWatch records and the practitioners' pollinator-friendly plant list (465 plants from 9 different sources; r = 0.52). We found pollinator-friendly plant lists to lack independence (correlation between practitioners' bumblebee-friendly and pollinator-friendly lists: r = 0.75), appropriateness and precision, thus failing to recognise the non-binary nature of food-plant preference (bumblebees used many plants, but only in small quantities, e.g. lavender—the most popular plant in the BeeWatch database—constituted, at most, only 11% of records for any one bumblebee species) and stark differences therein among species and pollinator groups. We call for the provision and use of up-to-date dynamic planting recommendations driven by live (citizen science) data, with the possibility to specify pollinator species or group, to powerfully support transformative personal learning journeys and pollinator-friendly management of garden spaces.
Hide Abstract

Identifying private gardens in the UK as key sites of environmental engagement, we look at how a longer-term online citizen science programme facilitated the development of new and personal understandings of nature. These were visible through new or renewed interest in wildlife-friendly gardening practices and attitudinal shifts in a large proportion of its participants. Qualitative and quantitative data, collected via interviews, focus groups, surveys and logging of user behaviours, revealed that cultivating a fascination with species identification was key to both 'helping nature' and wider learning, with the programme creating a space where scientific and non-scientific knowledge could co-exist and reinforce one another.
Hide Abstract

In recent years, the number and scale of environmental citizen science programmes that involve lay people in scientific research have increased rapidly. Many of these initiatives are concerned with the recording and identification of species, processes which are increasingly mediated through digital interfaces. Here, we address the growing need to understand the particular role of digital identification tools, both in generating scientific data and in supporting learning by lay people engaged in citizen science activities pertaining to biological recording communities. Starting from two well-known identification tools, namely identification keys and field guides, this study focuses on the decision-making and quality of learning processes underlying species identification tasks, by comparing three digital interfaces designed to identify bumblebee species. The three interfaces varied with respect to whether species were directly compared or filtered by matching on visual features; and whether the order of filters was directed by the interface or a user-driven open choice. A concurrent mixed-methods approach was adopted to compare how these different interfaces affected the ability of participants to make correct and quick species identifications, and to better understand how participants learned through using these interfaces. We found that the accuracy of identification and quality of learning were dependent upon the interface type, the difficulty of the specimen on the image being identified and the interaction between interface type and 'image difficulty'. Specifically, interfaces based on filtering outperformed those based on direct visual comparison across all metrics, and an open choice of filters led to higher accuracy than the interface that directed the filtering. Our results have direct implications for the design of online identification technologies for biological recording, irrespective of whether the goal is to collect higher quality citizen science data, or to support user learning and engagement in these communities of practice.
Hide Abstract

Several citizen science projects engage with the public around pollinator species, typically requesting data (eg in the form of photo-records of different species tagged by place and date). While such projects help scientists collect data, these data are rarely fed back to the public in any meaningful manner. In this paper, we address this through a recommender system based on Matrix Factorization over a matrix of observed bumblebee-plant interactions derived from data submitted to a citizen science project BeeWatch. The system recommends pollinator-friendly plants for domestic gardens and takes into account both the fact that different bumblebee species exhibit differing preferences for flowers, and that plants flower at different times of the year. The goal is to attract a range of bumblebee species to a garden and to ensure that these species have sufficient food sources through the season.
Hide Abstract

The rapid rise of citizen science, with lay people forming often extensive biodiversity sensor networks, is seen as a solution to the mismatch between data demand and supply whilst simultaneously engaging citizens with environmental topics. However, citizen science recording schemes require careful consideration of how to motivate, train and retain volunteers, especially where schemes concern species groups for which knowledge levels in society are low. We evaluated a novel computing science framework which allowed for the automated generation of textual feedback to citizen scientists using Natural Language Generation (NLG) technology. The feedback aimed at improving volunteerbs species identification skills and enhancing volunteer experience and retention; it used a species identification key and data collected from within a focal citizen science program to contextualize a submitted identification, explain reasons for any misidentification and highlight key features that facilitate correct identification. Here we report on experimental trials which show increased identification accuracy and enhanced retention of participants who were provided with automated feedback, compared to those who only received the correct identification without explanation. This feedback component has since been incorporated into BeeWatch, a citizen science program focused on bumblebee species in the UK, providing textual feedback for over 10,000 photo-submissions. The value of NLG feedback in the live program was captured through questionnaires (258 respondents) and through an evaluation of an online photo-based training tool designed to enhance identification skills (340 users). Our findings demonstrate that the automated generation of informative feedback fosters learning and volunteer engagement, thus paving the way for productive and long-lived citizen science projects.
Hide Abstract

We present an incremental Bayesian model which resolves key issues of crowd size and data quality for consensus labelling. We evaluate our method using data collected from a real world citizen science program, BeeWatch, which invites members of the public in the UK to classify (label) photographs of bumblebees as one of 22 possible species. The biological recording domain poses two key and hitherto unaddressed challenges for consensus models of crowdsourcing: (a) the large number of potential species makes classification difficult and (b) this is compounded by limited crowd availability, stemming from both the inherent difficulty of the task and the lack of relevant skills among the general public. We demonstrate that consensus labels can be reliably found in such circumstances with very small crowd sizes of around 3-5 users (i.e. through group sourcing). Our incremental Bayesian model, which minimizes crowd size by re-evaluating the quality of the consensus label following each species identification solicited from the crowd, is competitive with a Bayesian approach that uses a larger but fixed crowd size and outperforms majority voting. These results have important ecological applicability: biological recording programs such as BeeWatch can sustain themselves when resources such as taxonomic experts to confirm identifications by photo submitters are scarce (as is typically the case), and feedback can be provided to submitters in a timely fashion. More generally, our model provides benefits to any crowdsourced consensus labeling task where there is a cost (financial or otherwise) associated with soliciting a label.
Hide Abstract

To assess the ability of traditional biological recording schemes and lay citizen science approaches to gather data on species distributions and changes therein, we examined bumblebee records from across the UK. Relative abundances were determined for all species and distribution maps composed for the two most abundant ones: the widespread common carder (Bombus pascuorum) and the rapidly spreading tree bumblebee (B. hypnorum). Traditional biological recording scheme data were largely obtained from the national repository (NBN [National Biodiversity Network]), and citizen science data primarily from the photo-submission based BeeWatch initiative. Relative abundances of the bumblebee species from the two forms of recording were similar but their geographical spread was not. For the common carder, data from the traditional recording schemes were patchy, both spatially and across years, and tended to reflect the distribution of active record centres rather than the species distribution. BeeWatch records displayed more extensive geographic coverage, reflecting human population density and thus offering better opportunities to account for recording effort. For the tree bumblebee, both forms of recording revealed a rather similar spatial distribution due to a dedicated mapping project for this species which prevented naturalist records from being patchy. We recommend complementing recording by skilled naturalists with citizen science programmes where possible to obtain a nation-wide capability, and stress the need for timely uploading of all data in the national repository for policy and wider public use.
Hide Abstract

This paper explores the use of Natural Language Generation (NLG) for facilitating the provision of feedback to citizen scientists in the context of a nature conservation programme, BeeWatch. BeeWatch aims to capture the distribution of bumblebees, an ecologically and economically important species group in decline, across the UK and beyond. The NLG module described here uses comparisons of visual features of bumblebee species as well as contextual information to improve the citizen scientists' identification skills and to keep them motivated. We report studies that show a positive effect of NLG feedback on accuracy of bumblebee identification and on volunteer retention, along with a positive appraisal of the generated feedback.
Hide Abstract