The advancements in social networking have empowered open expression on micro-blogging platforms like Twitter. Traditional Twitter Sentiment Analysis (TSA) faces challenges due to rule-based or dictionary algorithms, dealing with feature selection, ambiguity, sparse data, and language variations. This study proposed a classification framework for Twitter sentiment data using word count vectorization and machine learning techniques to reduce the difficulties faced with annotated sentiment-labelled tweets. Various classifiers (Naïve Bayes (NB), Decision Tree (DT), K-Nearest Neighbors (KNN), Logistic Regression (LR), and Random Forest (RF)) were evaluated based on accuracy, precision, recall, F1-score, and specificity. Random Forest outperformed the others with an Area under Curve (AUC) value of 0.96 and an average precision (AP) score of 0.96 in sentiment classification, especially effective with minimal Twitter-specific features.
9 December 2025 in Computers in Biology and Medicine
In today’s world, the rapid growth of text data on web and online resources makes a challenging problem for the human beings to get the essential information. Finding such information can only be feasible by summarizing the text, known as Text summarization (TS). TS is the process of compressing the original text document without losing the core contents. Hence the most conventional and tricky method for summarization is to fetch the most informative or representative sentences from the original input document which is well-known as Extractive Text Summarization. It has the potential to obtain the valuable information in the shortest period of time. In this paper, three different nature-inspired algorithms such as Cuckoo search algorithm (CS), Firefly algorithm (FF) & Flower pollination algorithm (FP) are used to generate the summary for a document. The implementation is done over DUC 2003 dataset. However, the CS algorithm-based model is showing significantly better result than the other two models for this problem.