Using social media data to discover new potential Farmer-to-consumer (F2C) markets for the Australian agrifood industry- Amit Kumar

Project Member(s): Piccardi, M.

Funding or Partner Organisation: Food Agility CRC Limited (Food Agility CRC)
Food Agility CRC Limited (Food Agility CRC)

Start year: 2019

Summary: In this PhD project, we will use advanced AI and natural language processing (NLP) to automatically analyse social media data and discover and geolocate new potential F2C markets for the benefit of the Food Agility industry partners. The main objectives inlcude: 1. To Develop an NLP technology that can discover potential customers from social media data scraped from public accounts on Twitter, Facebook, Instagram and other social media. 2. To geolocate and estimate the size of the potential customer base from the posting's content. 3. To cater for large international markets such as China, India and Indonesia by including languages other than English in the analysis via automated translation.

Publications:

Kumar, A, Esmaili, N & Piccardi, M 2021, 'Topic-Document Inference With the Gumbel-Softmax Distribution', IEEE Access, vol. 9, pp. 1313-1320.
View/Download from: Publisher's site

Kumar, A, Esmaili, N & Piccardi, M 1970, 'A REINFORCEd Variational Autoencoder Topic Model', International Conference on Neural Information Processing, International Conference on Neural Information Processing, Springer International Publishing, Bali, Indonesia, pp. 360-369.
View/Download from: Publisher's site

FOR Codes: Natural Language Processing, Computer Software and Services not elsewhere classified, Information systems, technologies and services

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.