Aspect based Nepali Text Sentiment Analysis using BiLSTM

Aspect-Based Sentiment Analysis is a text analysis technique that classifies the sentiment of specific aspect in text. With rise internet and social media access, people tend to decide buy product or visit restaurant based on comments reviews. Categorical reviews can play significant role improving business if entity capture insights those use productively. Since Nepali low resource language there no numbers dataset for Therefore created work model target aspect-based review domain. The comprises extracted from sites, websites, manually prepared data. Data are cleaned, pre-processed then aspects sentiments using POS tagging. Sentiments categories classified word embedding deep learning BiLSTM model. classification into positive negative. 5 Food (F), Price (P), Service (S), Hygiene (H), Experience (E). result was found be good compared similar models other domains. prediction category attains F1 Score 0.88 0.76 respectively.