I read Physics at the University of Delhi, and Computer Science at the University of Cambridge before gained my PhD in Computational Linguistics at the University of Cambridge (2003). After Postdoctoral research at Columbia University and the University of Cambridge, I took up my first faculty position at the University of Aberdeen in 2009 before joining the Open University’s Knowledge Media Institute in 2017 as a Reader.
My research intersects Citizen Science, Artificial Intelligence and Data Science, facilitating societal access to information by mining, simplifying and summarising complex texts and by communicating data through language. I develop socially responsible AI technologies that bridge the divide between professional scientists and lay public, facilitate meaningful public engagement with science and foster attitudinal and behavioural change, particularly around biodiversity issues. I am the academic lead for three citizen science projects at the OU:
My current research investigates science learning within such citizen science projects, especially how citizens can learn alongside artificial intelligence from data. More details of my projects can be found at the Citizen Science and Artificial Intelligence group pages.
Our latest paper from BeeWatch Planting for Pollinators citizen science data has just been published in Nature Scientific Reports.
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. We used data gathered through our UK-wide citizen science programme (BeeWatch) to determine food plant use by the nations’ bumblebee species, and show that much of the plant use recorded does not reflect practitioner recommendations. Whilst communicated widely by organisations and readily taken up by gardeners, “pollinator-friendly” lists fail to recognise the stark differences among species and pollinator groups, or adapt to changing phenology or gardening practices. Our paper calls for the provision and use of up-to-date dynamic planting recommendations driven by live (citizen science) data to support pollinator-friendly management of garden spaces, and in the process transformative personal learning journeys through gardening.
The research was partially funded through the ongoing EPSRC Grant "Human-computer collaborative learning in citizen science" (EP/S027513/1). Principal Investigator Advaith Siddharthan said:
"Planting for Pollinators pioneered the use of AI technologies such as Recommender Systems in Citizen Science projects to offer data-driven pollinator-friendly gardening advice, and previously demonstrated its value in bringing about attitudinal change in citizens (Sharma et al. 2019). This paper additionally demonstrates the scientific value of the data collected through citizen science."
To find out more, read the paper below:
Citizen science data reveals the need for keeping garden plant recommendations up-to-date to help pollinators (2020) Helen B Anderson, Annie Robinson, Advaith Siddharthan, Nirwan Sharma, Helen Bostock, Andrew Salisbury, Stuart Roberts and René van der Wal. Scientific Reports volume 10, Article number: 20483
As the COVID-19 pandemic puts the focus on literacy and numeracy in home-schooling, KMi researchers have developed technologies to also help families learn about the natural environment.
The Human-Computer Collaborative Learning in Citizen Science (X-Polli:Nation) project, which received £507,000 from the Engineering and Physical Research Council has responded to the pandemic by creating a new collection of interactive learning materials on the Open University’s OpenLearn Create Platform.
The course, A Cross-pollinated resource for pollinator citizen science, is being launched today at the beginning of Bees’ Needs Week (July 13-19 2020), an annual event coordinated by the Department for Environment, Food and Rural Affairs, working alongside charities, businesses, conservation groups and academic institutions to raise awareness of bees and other pollinators.
Innovative technologies and interactive interfaces
These courses, which are suitable for children aged seven and above and their parents and teachers, are designed around innovative research technologies developed through the project (by Nirwan Sharma, Stefan Rüger and Advaith Siddharthan), which investigates how Artificial Intelligence (AI) technologies can work alongside human intelligence in monitoring our natural environment and how people and AI can help each other in science learning.
The materials make it possible to learn to identify and distinguish different species of bumblebee and butterfly using an interactive identification key, seeking suggestions from automated image recognition and receiving formative feedback through automatically generated texts. There are also interfaces to explore which flowers attract which pollinators, and advice on what to plant is delivered through a recommender system.
As the research project develops novel technologies that mediate formal and non-formal science learning, indoor and outdoor learning, and home and school learning, this OpenLearn Create collection provides a fantastic and timely way for families and schools to explore these. We hope that learning about the diversity of pollinating insects can open a door to greater enjoyment of nature and spur societal action to protect it.
The learning materials and the wider project are part of a collaboration in X-Polli:Nation citizen science between The Open University, University of Aberdeen, Imperial College London, Learning through Landscapes, St Alban’s CE Aided Primary School and Museo Di Storia Naturale Della Maremma.
Sensory Explorations of Nature in School Environments. This project seeks to augment nature observation outdoors through developing variable-friction haptic interfaces that allow you to feel texture when touching an image on the screen... Read more
Partners: Imperial College London, University of Edinburgh, Learning through Landscapes.
Delivering Enhanced Biodiversity Information with Adaptive Citizen Science and Intelligent Digital Engagements. This project seeks to construct good biodiversity models generated from available data, communicate these models well, and preferentially target effort to add records from times and places that optimally improve the model outputs...Read more
Partners: Centre for Ecology and Hydrology (Lead), University of York, University of Warick, et al.
Funder: EU H2020
Co-designed citizen observatories for the EOS-Cloud. This project aims to design, prototyped and implemented services that address the Open Science challenges shared by Citizen observatories of biodiversity, based on the experience of participating platforms such as iSpot Nature...Read more
Partners: Agencia estatal consejo superior deinvestigaciones cientificas (Lead), Conservation education and research trust, et al.
This project explores the potential for collaborative learning between humans and machines within the framework of environmental citizen science....Read more
Partners: Imperial College London, University of Aberdeen, Learning through Landscapes, St Alban's CoE Primary School.
Funder: National Geographic
X:Polli-Nation (pronounced cross-pollination) is a biodiversity citizen science project embedded in primary schools...Read more
Partners: Imperial College London (Lead), University of Aberdeen, Learning through Landscapes, St Alban's CoE Primary School, Natural History Museum of Maremma.
Ao, S., RÃ¼ger, S and Siddharthan, A. (2023) Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection, 2023 IJCAI Joint Workshop on Artificial Intelligence Safety and Safe Reinforcement Learning, AISafety-SafeRL, Macau, China
Schiller, D, Yu, A, Alia-Klein, N, Becker, S, Cromwell, H, Dolcos, F, Eslinger, P, Frewen, P, Kemp, A, Pace-Schott, E, Raber, J, Silton, R, Stefanova, E, Williams, J, Abe, N, Aghajani, M, Albrecht, F, Alexander, R, Anders, S, AragÃ³n, O, Arias, J, Arzy, S, Aue, T, Baez, S, Balconi, M, Ballarini, T, Bannister, S, Banta, M, Barrett, K, Belzung, C, Bensafi, M, Booij, L, Bookwala, J, Boulanger-Bertolus, J, Boutros, S, BrÃ¤scher, A, Bruno, A, Busatto, G, Bylsma, L, Caldwell-Harris, C, Chan, R, Cherbuin, N, Chiarella, J, Cipresso, P, Critchley, H, Croote, D, Demaree, H, Denson, T, Depue, B, Derntl, B, Dickson, J, Dolcos, S, Drach-Zahavy, A, DubljeviÄ‡, O, Eerola, T, Ellingsen, D, Fairfield, B, Ferdenzi, C, Friedman, B, Fu, C, Gatt, J, deGelder, B, Gendolla, G, Gilam, G, Goldblatt, H, Gooding, A, Gosseries, O, Hamm, A, Hanson, J, Hendler, T, Herbert, C, Hofmann, S, Ibanez, A, Joffily, M, Jovanovic, T, Kahrilas, I, Kangas, M, Katsumi, Y, Kensinger, E, Kirby, L, Koncz, R, Koster, E, Kozlowska, K, Krach, S, Kret, M, Krippl, M, Kusi-Mensah, K, Ladouceur, C, Laureys, S, Lawrence, A, Li, C, Liddell, B, Lidhar, N, Lowry, C, Magee, K, Marin, M, Mariotti, V, Martin, L, Marusak, H, Mayer, A, Merner, A, Minnier, J, Moll, J, Morrison, R, Moore, M, Mouly, A, Mueller, S, MÃ¼hlberger, A, Murphy, N, Muscatello, M, Musser, E, Newton, T, Noll-Hussong, M, Norrholm, S, Northoff, G, Nusslock, R, Okon-Singer, H, Olino, T, Ortner, C, Owolabi, M, Padulo, C, Palermo, R, Palumbo, R, Palumbo, S, Papadelis, C, Pegna, A, Pellegrini, S, Peltonen, K, Penninx, B, Pietrini, P, Pinna, G, Lobo, R, Polnaszek, K, Polyakova, M, Rabinak, C, HeleneRichter, S, Richter, T, Riva, G, Rizzo, A, Robinson, J, Rosa, P, Sachdev, P, Sato, W, Schroeter, M, Schweizer, S, Shiban, Y, Siddharthan, A., Siedlecka, E, Smith, R, Soreq, H, Spangler, D, Stern, E, Styliadis, C, Sullivan, G, Swain, J, Urben, S, Stock, J, Kooij, M, Overveld, M, Rheenen, T, VanElzakker, M, Ventura-Bort, C, Verona, E, Volk, T, Wang, Y, Weingast, L, Weymar, M, Williams, C, Willis, M, Yamashita, P, Zahn, R, Zupan, B, Lowe, L, Gabriela, G, F, H and Leonie, L (2023) The Human Affectome, pp. (Early access), Elsevier
Ao, S., Rueger, S. and Siddharthan, A. (2022) Confidence-Aware Calibration and Scoring Functions for Curriculum Learning, 2022 15th International Conference on Machine Vision., Rome, Italy
Sharma, N., Siddharthan, A., Colucci-Gray, L and Wal, R (2022) Consensus building in on-line citizen science, 25th ACM Conference On Computer-Supported Cooperative Work And Social Computing (CSCW 2022), Online
Lotz, N, Siddharthan, A., Priola, C and Wallace, J (2022) Gender equality work in a distance learning institution, Diversity Interventions 2022, Oxford