In the age of big data, there is increasing growth of data on the Internet. It becomes frustrating for users to locate the desired data. Therefore, text summarization emerges as a solution to this problem. It summarizes and presents the users with the gist of the provided documents. However, summarizer systems face challenges, such as poor grammaticality, missing important information, and redundancy, particularly in multi-document summarization. This study involves the development of a graph-based extractive generic MDS technique, named Grapharizer (GRAPH-based summARIZER), focusing on resolving these challenges. Grapharizer addresses the grammaticality problems of the summary using lemmatization during pre-processing. Furthermore, synonym mapping, multi-word expression mapping, and anaphora and cataphora resolution, contribute positively to improving the grammaticality of the generated summary. Challenges, such as redundancy and proper coverage of all topics, are dealt with to achieve informativity and representativeness. Grapharizer is a novel approach which can also be used in combination with different machine learning models. The system was tested on DUC 2004 and Recent News Article datasets against various state-of-the-art techniques. Use of Grapharizer with machine learning increased accuracy by up to 23.05% compared with different baseline techniques on ROUGE scores. Expert evaluation of the proposed system indicated the accuracy to be more than 55%.

In classification tasks, it is presumed that the number of classes of observations is balanced. While classification models usually give a heavily biased weight to the class that has higher occurrence, building an efficient classification model is likely a challenge when feeding it with imbalanced dataset observations or samples of data. This study introduces a new method for addressing imbalanced datasets in classification tasks, particularly focusing on predicting long-term deposits in banking institutions. The method involves systematic evaluation and comparison of random oversampling (ROS) and synthetic minority over-sampling technique (SMOTE) while employing meticulous feature selection to optimize classification precision. This new methodology showcased competitive performance, notably achieving an accuracy of 89.1% and a G-mean of 0.61 with SMOTE at a 500% ratio encompassing all features in Experiment 2 and an accuracy of 87.2% and a G-mean of 0.677 with ROS at a 500% ratio using the top 15 features in Experiment 3. Keywords: Synthetic Minority Oversampling Technique, Random Oversampling, Imbalanced Data, Feature Selection, Random Forest DOI：https://doi.org/10.35741/issn.0258-2724.58.6.21