Use of twitter data for waste minimisation in beef supply chain

Abstract

Approximately one third of the food produced is discarded or lost, which accounts for 1.3 billion tons per annum. The waste is being generated throughout the supply chain viz. farmers, wholesalers/processors, logistics, retailers and consumers. The majority of waste occurs at the interface of retailers and consumers. Many global retailers are making efforts to extract intelligence from customer's complaints left at retail store to backtrack their supply chain to mitigate the waste. However, majority of the customers don't leave the complaints in the store because of various reasons like inconvenience, lack of time, distance, ignorance etc. In current digital world, consumers are active on social media and express their sentiments, thoughts, and opinions about a particular product freely. For example, on an average, 45,000 tweets are tweeted daily related to beef products to express their likes and dislikes. These tweets are large in volume, scattered and unstructured in nature. In this study, twitter data is utilised to develop waste minimization strategies by backtracking the supply chain. The execution process of proposed framework is demonstrated for beef supply chain. The proposed model is generic enough and can be applied to other domains as well.

Event classification and location prediction from tweets during disasters

“…Social media platforms can be efficiently used for supply chain management by professionals, organizations, and retailers for their operations (Chae 2015;Mishra and Singh 2016;Papadopoulos et al 2017). Social networks like Twitter and Facebook allow users to update information on social activities that they undertake .…”

The interconnectedness of the economic content in the speeches of the US Presidents

“…The evidence from Figure 6, together with the high clustering indica- tors, assortativity and the slightly bimodal degree and strength distributions suggest the presence of another higher order structure that can further characterize the structure of the considered network. In particular, a positive value of strength assortativity with a noticeable degree of heterogeneity suggests the presence of a core-periphery structure called rich-club (Zhou and Mondragón, 2004 (2019). In this one, we assess rich-club ordering in the case of node strength and we measure the density of connections among nodes with the highest strength φ(s).…”

“…Nowadays, textual analysis is employed in a wide variety of studies, for example in medicine Lee et al (2019), in tourism management analysis Cheng and Jin (2019), in designing recommendation systems Ji et al (2019), in analyzing countries' foreign policies Cannon et al (2018), in investigating the blog users' sentiments during rainstorm and waterlogging disasters Wu et al (2018) or in understanding the potential applications and users of augmented reality tools Li et al (2018). Feuerriegel and Gordon (2018) highlight the importance of the information contained in written documents to analyse the economic paths and to forecast economic and financial variables.…”

“…Furthermore, it is worthy to mention the case of Kahveci and Odabaş (2016), in which the textual analysis has been employed to explore the semantic of monetary policy documents from the Federal Reserve Board, In a more general economic and financial framework we can evidence many works that deepen text mining on the analysis of stock markets, stock returns, trading and, more generally, on the ability of transforming qualitative variables into quantitative measures to improve financial fore-casts and market predictions (see, e.g. Blasco et al, 2005;Schumaker and Chen, 2009;Groth and Muntermann, 2011;Huang and Li, 2011;Loughran and McDonald, 2016;Mishra and Singh, 2018).…”

Smart Monitoring and Controlling of Government Policies Using Social Media and Cloud Computing

“…Sentiment analysis is often regarded as most effective tool to map public response towards an entity (Joseph et al 2017). Sentiment analysis is defined as a text analytic technique which deals with extraction of sentiment from given piece of text (Liu 2012;Mishra and Singh 2016). Unlike the previous analysis, the upcoming analysis requires preprocessing of data.…”