Modeling the Onion Market Using Sentiment Analysis with Deep Learning

Abstract

This study analyzed the effect of the sensitivity of news related to onions on producers' decision-making on cultivation areas and market supply and demand. We collected onion-related article data and derived the sentiment index through sentiment analysis using neural networkbased learning. We estimated the cultivation area function, including the sentiment index we made. We analyzed the impact of news sensitivity on the onion market by constructing an onion market supply and demand model. Then, we gave a sentiment index shock to the cultivation area to examine the impact on the onion market. We also explored the sensitivity analysis to emphasize the news in June, July, and August plays an important role in the supply side. To the best of our knowledge, our approach using sentiment index in the agricultural model is the first trial. Therefore, our study can introduce an approach to improve the accuracy of modeling for agriculture and apply it to the area of agricultural economics.

Advancing Agricultural Predictions: A Deep Learning Approach to Estimating Bulb Weight Using Neural Prophet Model

“…Soon and Kim [7] used an artificial-neural-network (ANN) language model to collect real-time African swine fever news, create a sentiment index, and analyze the impact of African swine fever on meat prices via an autoregressive lag distribution model (ARDL). Cho et al [8] derived an onion sentiment index from articles related to onions before sowing. By incorporating the onion sentiment index into an onion supply model, they analyzed the impact of changes in the onion sentiment index on the onion market.…”