{"title":"Digital Crop Health Monitoring by Analyzing Social Media Streams","authors":"Priyamvada Shankar, Christian Bitter, M. Liwicki","doi":"10.1109/AI4G50087.2020.9310985","DOIUrl":null,"url":null,"abstract":"This paper introduces the idea of using social media streams like Twitter to identify occurrences of crop diseases. Climate change and changes in agriculture practices have contributed to a change in crop disease dynamics leading to an increase in crop damages. Monitoring crop disease occurrences across regions is helpful for farmers to prepare for such adverse situations and make effective use of crop protection products thus ensuring enough produce for the growing population and protection of the environment. We investigate Machine Learning and Natural Language Processing techniques in order to spot agricultural discussions on Twitter; then analyze, categorize, and group them; so they can be used by a stakeholder to identify crop disease incidences, patterns, and trends at the regional scale. Current systems using keyword based search of agricultural diseases do not always yield agriculturally relevant tweets and those that do could talk on a range of sub-topics. Therefore, text classification forms the core component of this work. A two fold classification process is employed, classifying agriculturally relevant tweets from the rest and then performing fine-grained categorization on them. The resulting model for agricultural tweets classification performs with 93% accuracy and the fine grained categorization model that categorizes tweets into 6 categories gives 75% accuracy. A prototype of an interactive web based disease monitoring application is also presented. The location estimation is not always accurate but nonetheless, this work acts as a proof of concept for the introduction of social media as a novel data source in precision farming.","PeriodicalId":286271,"journal":{"name":"2020 IEEE / ITU International Conference on Artificial Intelligence for Good (AI4G)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE / ITU International Conference on Artificial Intelligence for Good (AI4G)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AI4G50087.2020.9310985","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
This paper introduces the idea of using social media streams like Twitter to identify occurrences of crop diseases. Climate change and changes in agriculture practices have contributed to a change in crop disease dynamics leading to an increase in crop damages. Monitoring crop disease occurrences across regions is helpful for farmers to prepare for such adverse situations and make effective use of crop protection products thus ensuring enough produce for the growing population and protection of the environment. We investigate Machine Learning and Natural Language Processing techniques in order to spot agricultural discussions on Twitter; then analyze, categorize, and group them; so they can be used by a stakeholder to identify crop disease incidences, patterns, and trends at the regional scale. Current systems using keyword based search of agricultural diseases do not always yield agriculturally relevant tweets and those that do could talk on a range of sub-topics. Therefore, text classification forms the core component of this work. A two fold classification process is employed, classifying agriculturally relevant tweets from the rest and then performing fine-grained categorization on them. The resulting model for agricultural tweets classification performs with 93% accuracy and the fine grained categorization model that categorizes tweets into 6 categories gives 75% accuracy. A prototype of an interactive web based disease monitoring application is also presented. The location estimation is not always accurate but nonetheless, this work acts as a proof of concept for the introduction of social media as a novel data source in precision farming.