Sentiment Analysis for Language Acquisition Based on Random Forest Model

Language skills are an important training skill in higher education. In higher vocational education, the importance of foreign language education has become increasingly prominent. The author constructs a model suitable for social media text sentiment analysis from the dimensions of the research object, the selection of learning effectiveness indicators and the direction of algorithm selection. It uses a recurrent neural network (RNN) and uses annotated emotional data sets for model training to obtain high-level results. An emotional classifier for vocational students' language learning attitude. Based on the emotional analysis results, the data set is divided into different emotional state groups, such as happiness, depression, anxiety, etc., and the machine learning algorithm Random Forest (RandomForest) is used to explore students in different emotional states. The relationship between language learning effectiveness and engagement. The research results show that making timely adjustments to higher vocational students through prediction and improving learning efficiency can promote better and faster development of English learning for higher vocational students.