Semantics Analysis of Agricultural Experts' Opinions for Crop Productivity through Machine Learning

• Published in: Applied artificial intelligence Vol. 36; no. 1
• Main Authors: Rehman, Mehak, Razzaq, Abdul, Baig, Irfan Ahmad, Jabeen, Javeria, Tahir, Muhammad Hammad Nadeem, Ahmed, Umar Ijaz, Altaf, Adnan, Abbas, Touqeer
• Format: Journal Article
• Language: English
• Published: Philadelphia Taylor & Francis 31.12.2022; Taylor & Francis Ltd; Taylor & Francis Group
• Subjects: Agriculture; Artificial intelligence; Clustering; Crop yield; Data collection; Data mining; Machine learning; Natural language processing; Productivity; Semantics; Sentiment analysis; Soils; Stock exchanges; Tillage
• ISSN: 0883-9514; 1087-6545
• DOI: 10.1080/08839514.2021.2012055

Semantic analysis is a particular technique, which is an interesting area of research that associates with Natural Language Processing (NLP), artificial intelligence, opinion mining, text clustering, and classification. Numerous text processing techniques are being used to find out sentiments from the comments, such as social media tweets, hoax, fiction, nonfiction, novels, books, movies, health care, and stock exchange. Agrarian experts' opinions play a vital role in the agriculture sector that yields good crop productivity. This paper presents a descriptive analysis of agriculture experts' opinions through machine learning methods based on textual data collection. The data has been collected by surveying various academia, research institute, and industry of Punjab, Pakistan. The impact of various agricultural inputs such as seed quality, soil quality, soil-intensive tillage, climate changes, water shortage, synthetic fertilizer, and precision technologies on crop productivity have been collected through questionnaires. This research provides a descriptive analysis of collected agrarians experts opinions to increase the crop yield by providing awareness regarding current agriculture inputs to farmers by using machine learning. The current research provides a cohesive expert guideline for improving crop productivity, useful for agricultural policymaking, and conveys adequate farmers' knowledge. Consequently, the proposed method is an innovative way of discovering recommendations of agrarians through sentiment analysis in survey data using machine learning methods. Furthermore, to the best of our knowledge, agrarians experts opinions on enhancing crop productivity have been considered for the first time in Pakistan.