Systematic Literature Review on Sentence Level Sentiment Analysis

—Sentiment analysis is the task of determining the sentiment expressed in a given text. It has gained significant attention in recent years due to its applications in various domains such as social media analysis, customer feedback analysis, and opinion mining. While many studies focus on document-level sentiment analysis, the analysis of sentiments at the sentence level provides a more fine-grained understanding of text sentiment. This paper presents a systematic literature review (SLR) on sentence-level sentiment analysis, employing the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The objective of this study is to identify the state-of-the-art techniques, methodologies, datasets, and evaluation metrics used in sentence-level sentiment analysis studies published between 2010 and 2022. The SLR methodology involves a comprehensive search across multiple databases, such as Research Gate, Science Direct, Dimensions and Google Scholar, to retrieve relevant papers. A rigorous inclusion and exclusion criteria are applied to ensure the selection of papers that specifically address sentence-level sentiment analysis. Data extraction and synthesis are performed to capture essential information, including the contribution facets, types of datasets used, and evaluation metrics utilized. The findings of this SLR reveal several significant trends and advancements in sentence-level sentiment analysis. Various machine learning techniques have been widely adopted for sentiment classification at the sentence level. Additionally, the availability of large-scale annotated datasets, such as Tweets and Movie Review dataset, has played a crucial role in improving the performance of sentiment analysis models. Furthermore, evaluation metrics and benchmarks have emerged to assess the effectiveness of different models, including accuracy, precision, recall, F1-score, and AUC. This research paper contributes to the existing literature by pr