Lexicon and Deep Learning-Based Approaches in Sentiment Analysis on Short Texts

Social media is an essential component of our personal and professional lives. We use it extensively to share various things, including our opinions on daily topics and feelings about different subjects. This sharing of posts provides insights into someone’s current emotions. In artificial intelligence (AI) and deep learning (DL), researchers emphasize opinion mining and analysis of sentiment, particularly on social media platforms such as Twitter (currently known as X), which has a global user base. This research work revolves explicitly around a comparison between two popular approaches: Lexicon-based and Deep learning-based Approaches. To conduct this study, this study has used a Twitter dataset called sentiment140, which contains over 1.5 million data points. The primary focus was the Long Short-Term Memory (LSTM) deep learning sequence model. In the beginning, we used particular techniques to preprocess the data. The dataset is divided into training and test data. We evaluated the performance of our model using the test data. Simultaneously, we have applied the lexicon-based approach to the same test data and recorded the outputs. Finally, we compared the two approaches by creating confusion matrices based on their respective outputs. This allows us to assess their precision, recall, and F1-Score, enabling us to determine which approach yields better accuracy. This research achieved 98% model accuracy for deep learning algorithms and 95% model accuracy for the lexicon-based approach.

Multiple Image Watermarking with Discrete Cosine Transform

Multiple image watermarking is an advanced concept of singular watermarking techniques. The existing singular digital image watermarking techniques cannot obtain all the design goals, such as imperceptibility, robustness, security, and capacity simultaneously with perfection. Hence, the multiple image watermarking technique is designed that embeds several watermarks into the same host image for conveying multiple information. This paper proposed a multiple image watermarking technique with Discrete Cosine Transform (DCT) for ensuring the low computational time for embedding, encryption, decryption as well as extraction of the watermark images. Here, DCT is used to ensure the visual quality of the host image, and a random binary matrix is used to improve the security of the digital image. We have given a basic framework for multiple image watermarking. Our experimental results show satisfactory performance.

CT-Scan Findings of Hepatic Mass Patients Attending at a Tertiary Care Hospital in Bangladesh

Background: CT-scan is a very useful diagnostic tool for the detection of hepatic mass. Objective: The present study was undertaken to determine the CT-scan findings of benign and malignant hepatic mass patients. Methodology: This was a cross sectional study conducted in Radiology and Imaging Department at Mymensingh Medical College Hospital (MMCH), Mymensingh;Dhaka Medical College Hospital (DMCH), Dhaka and Banghabandhu Sheikh Mujib Medical University (BSMMU), Dhaka with the collaboration of Pathology Department of the same institute for histopathological confirmation. This study was carried out from January 2006 to December 2007 for a period of 2 years. The patients who were clinically suspected of having hepatic mass attended in the Radiology and Imaging Department in the above mentioned institutes were included as study population. All the CT-scan findings were recorded. Result: A total number of 50 patients were enrolled for this study. CT-scan was done among 40 males and 10 females with a mean age of 51.28 years old. Hypodensity was found in 17 (60.7%) and 18 (81.8%) cases in malignant and benign hepatic lesions respectively. Ill-defined margin was detected in 12 (42.9%) and 6 (27.3%) cases respectively. Calcification was present on 11 (39.3%) malignant lesion and 6 (27.3%) benign lesions. Pressure effect on biliary apparatus was found in 11 (39.3%) malignant lesions and 1 (4.5%) benign lesions (p < 0.05). Lymphadenopathy was found in 10 (35.7%) malignant lesions and 1 (4.5%) benign lesions (p < 0.05). Conclusion: In conclusion, CT-scan findings of malignant and benign hepatic mass show hypodensity with more contrast enhancement in malignant lesions with more calcification in malignant lesion;however, significant difference is detected in pressure effect on biliary apparatus and lymphadenopathy.

Post-Operative Mortality after Ileal Perforation at a Teaching Hospital in Dhaka City

Background: Ileal perforation is a very critical condition. Objectives: The purpose of the present study was to see the post-operative mortality after ileal perforation. Methodology: This prospective cohort study was conducted in the Department of Surgery at Dhaka Medical College Hospital, Dhaka, Bangladesh from September 2000 to December 2002 for period of 2 years and 3 months. All the patients presented with ileal perforation at any age with both sexes were included in this study. Patients were selected consecutively and the patients who showed ileal perforation at laparotomy were included in this study. Preoperative diagnosis was based on detailed history, complete physical examinations supported by plain x-ray abdomen in erect posture including both domes of diaphragm. After immediate resuscitation surgical treatment was undertaken as soon as possible following admission in all cases. The patients were followed up and the mortality profiles were recorded after surgical intervention. Result: Out of 53 patients having postoperative complications 38 patients were survived and 15 patients were expired. So total survivors were 85% and non-survivors 15%. In this study most of the mortality (12%) was attributed to septicemia and mode of death was multiple organ failure. Respiratory complications caused 2% mortality one patient died of ARDS and another elderly patient with preexisting bronchial asthma developed respiratory failure and was unresponsive to treatment. One death was related to faecal fistula followed by severe fluid, electrolyte and acid-base imbalance with peritonitis and gross sepsis. Conclusion: In conclusion, the mortality is significantly high due to septicemia, ARDS and faecal fistula.