Abstract:
Sentiment analysis refers to the evaluation of any text, word, or other. Sentiment analysis, which is also defined as opinion mining, is a method of natural language processing (NLP) that determines the emotional subtext of a body of text. Numerous organizations use this method to identify and categorize customer opinions about a given good, service, or concept. Text is mined for sentiment and qualitative data using machine learning (ML), artificial intelligence (AI), and data mining methods. Opinion mining can extract the content, opinion holder, and polarity (or the quantity of positivity and negativity) from text in addition to identifying sentiment. Additionally, other perspectives, including article, paragraph, sentence, and sub-sentence divisions, can be utilized for sentiment analysis. The expansion of social media platforms is creating a ton of texts and grabbing people's attention. From such data, Sentiment Analysis (SA) derives informative information. The majority of study on SA has been conducted in English, but Bengali and other important languages are also required. Because Bengali is the fifth most often spoken language among native speakers and is extensively implemented on social media, it is crucial to concentrate on Bengali social posts and comments. Despite the large number, Bengali Sentimental Analysis has seen some minor progress. But creating an automated method for classifying emotions in low- resource languages like Bengali is a crucial task. The task is made more difficult by a lack of resources and benchmark corpora. Consequently, creating a benchmark for the development of an emotion classifier for Bengali texts requires a corpus. A total of 5000 texts are labeled into 11 basic emotion categories such as anger, fear, surprise, sad, happy, disgust, funny, abusive, advice, neutral and praise. Our study's primary goal is to more specifically identify the emotions expressed in sentences and comments that are written in Bengali. We selected Eleven classifications for this reason in order to more precisely and accurately define the emotions.
