Research on agricultural monitoring system based on convolutional neural network

Dynamic impact of negative public sentiment on agricultural product prices during COVID-19

“…The online negative public sentiment was found to most affect vegetable prices, followed by the aquatic product and fruit prices, with the smallest impact being on the livestock product prices, which verified Hypothesis 1 . These results were similar to those in Chen et al (2018) and Nicola et al (2020) , but in conflict with Shi et al (2020) , which found that the disease had the most significant impact on livestock product price fluctuations. Even though many people were buying larger than normal quantities of livestock products due to early panic buying, because of the relatively high livestock product prices, the number of larger purchases was limited ( Yadav and Pathak, 2017 ), which meant that any livestock product price changes in response to the public online negative sentiment were relatively small.…”

“…For example, Strauβ et al (2016) used the Granger causality test to study the relationships between the emotions in Dutch newspaper articles and stock market prices, and found that negative emotions better reflected the stock market trends, Kraaijeveld and De Smedt (2020) also used the Granger causality test to determine whether Twitter emotions predicted bitcoin, Li et al (2020b) concluded that the direct measurement of investor sentiment constructed by leveraging user generated messages and text mining methods had some predictive power in the Chinese stock market, and Li et al (2020a) improved the accuracy of stock price predictions by building a new stock prediction system that combined technical stock price indicators and the sentiments expressed in news articles. The sentiment influences on agricultural market price behaviors have also been examined; for example, Hassouneh et al (2012) developed an avian influenza food panic information index to analyze the impact of the avian influenza epidemic on vertical poultry prices in Egypt, Chen et al (2018) calculated the positive and negative emotional tendency values on social networks and tested the Granger causality between the emotions and vegetable prices, and Zeng et al (2019) used a TVP-VAR model to study the impact of the media reported negative emotions on agricultural product price fluctuations, and the time, region, and product impact differences.…”

Dynamic Influence of Network Public Opinions on Price Fluctuation of Small Agricultural Products Based on NLP-TVP-VAR Model—Taking Garlic as an Example

“…Hassouneh et al [44] developed an avian influenza food panic information index to analyze the impact of the avian influenza epidemic on vertical poultry prices in Egypt. Chen et al [45] calculated the positive and negative emotional tendency values on social networks based on CNN and tested the Granger causality between emotions and vegetable prices. Hsl et al [46] analyzed the relationships between African swine fever (ASF) and meat prices based on a TVP-VAR model, and the results showed that there were some differences in the impact size, direction and duration of ASF on the prices of pork, chicken, beef and mutton.…”

A Bibliometric Analysis of Literature on Vegetable Prices at Domestic and International Markets—A Knowledge Graph Approach

“…Scholars are based on HP filtering the hybrid neural network structure of the processor [39] predicts the price of vegetables in linear and nonlinear modes, effectively reducing the risk of vegetable farmers; scholars also combine the fruit fly algorithm (FOA) with the induced ordered weighted average (IWOA), improve the prediction accuracy [40], by establishing a seasonal SARIMA model to predict the monthly price of tomato wholesale prices [32]. In addition, some scholars link internet public opinion with vegetable prices, and construct a combined volume through analysis of internet public opinion the mixed prediction model of product neural network and corpus, and eliminate the seasonal effect of price [41], combined with natural language processing (NLP), convolutional neural network (CNN) and classic economic methods, to carry out large-scale public opinion Subject modeling, research shows that online public opinion has an impact on the fluctuation of vegetable prices, which can be used as a potential factor in predicting vegetable prices [42]. In addition, seven indicators are selected using the ICAVP algorithm to establish a better vegetable price early warning system [43].…”