Twitter¹ is a micro-blogging website which provides platform for people to share and express their views about topics, happenings, products and other services. Tweets can be classified into different classes based on their relevance with the topic searched. Various Machine Learning algorithms are currently employed in classification of tweets into positive and negative classes based on their sentiments, such as Baseline, Naive Bayes Classifier, Support Vector Machine etc. This paper contains implementation of Naive Bayes using sentiment140 training data using Twitter database and propose a method to improve classification. Use of SentiWordNet along with Naive Bayes can improve accuracy of classification of tweets, by providing positivity, negativity and objectivity score of words present in tweets. For actual implementation of this system python with NLTK and python-Twitter APIs are used.

Objective: The largest pandemic in history, the COVID-19 pandemic, has been declared a doomsday globally. The second wave spreading worldwide has devastating consequences in every sector of life. Several measures to contain and curb its infection have forged significant challenges for the education community. With an estimated 1.6 billion learners, the closure of schools and other educational institutions has impacted more than 90% of students worldwide from the elementary to tertiary level. Methods: In a view to studying impacts on student’s fraternity, this article aims at addressing alternative ways of educating—more specifically, online education—through the analysis of Google trends for the past year. The study analyzed the platforms of online teaching and learning systems that have been enabling remote learning, thereby limiting the impact on the education system. Thorough text analysis is performed on an existing dataset from Kaggle to retrieve insight on the clustering of words that are more often looked at during this pandemic to find the general patterns of their occurrence. Findings: The results show that the coronavirus patients are the most trending patterns in word search clustering, with the education system being at the control and preventive measures to bring equilibrium in the system of education. There has been significant growth in online platforms in the last year. Existing assets of educational establishments have effectively converted conventional education into new-age online education with the help of virtual classes and other key online tools in this continually fluctuating scholastic setting. The effective usage of teaching tools such as Microsoft Teams, Zoom, Google Meet, and WebEx are the most used online platforms for the conduction of classes, and whiteboard software tools and learning apps such as Vedantu, Udemy, Byju’s, and Whitehat Junior have been big market players in the education system over the pandemic year, especially in India. Conclusions: The article helps to draw a holistic approach of ongoing online teaching-learning methods during the lockdown and also highlights changes that took place in the conventional education system amid the COVID pandemic to overcome the persisting disruption in academic activities and to ensure correct perception towards the online procedure as a normal course of action in the new educational system. To fill in the void of classroom learning and to minimize the virus spread over the last year, digital learning in various schools and colleges has been emphasized, leading to a significant increase in the usage of whiteboard software platforms.

Water is an important resource for life and its existence and, unfortunately, large quantities of water are being wasted on a daily basis. Monitoring the consumption of water can control water usage, and smart technologies can play a useful role. In this paper, a smart system based on Internet of Things (IoT) has been proposed to monitor the water consumption in an urban housing complex. An ultrasonic sensor, together with Arduino, continuously monitors the water level of water tanks on rooftops and sends these data to a server through a Wi-Fi module. Using the data collected from the IoT system, the daily and weekly average water requirement of households can be calculated. Support vector machines (SVM) are used to forecast water consumption. The observed readings are divided into training and testing datasets. Water consumption is predicted for each day for a user. Error is recorded as the difference between the actual consumption and the predicted value, and it decreases as the number of days increase. An algorithm to monitor leakage of water in the tanks has also been proposed. A web interface allows the user to visualize the water usage, monitor their consumption, and detect any leakage and leakage rate in the system.

A certificate is a document that is received once the person completed a particular course. This certificate can be used to get a job or to get admitted to an institute/university of higher studies. Most of the institutes/universities do not have a mechanism in the admission system that can catch forged certificates. Hence, a system that can store certificates on the blockchain and stop the admission forgery through fake certificates is required. The proposed framework is based on blockchain technology that improves security, transparency, etc., and reduces the cost. To overcome the problem of fake certification, a chain of blocks is created for certificates that are immutable as well as transparent amongst all the nodes in the system. This paper presents a step-by-step development process for a certificate verification system using blockchain technology. The key component of this system is a smart contract. A Smart contract Certi has been developed for storing certificates by using a text editor Sublime Text3 and an IDE Remix Ethereum. The validity of the stored certificates can be checked by the employer or admission team at the time of recruitment or admission using Certi smart contract. Blockchain technology possesses its transparency feature hence at the same time the same data on the certificate can be seen by the employer, admission team as well as student itself.

Document clustering is a traditional technique, and is used in multiple fields like data mining, information retrieval, knowledge discovery from data, pattern recognition etc. Large volumes of textual data being created in the modern world have resulted in the rise in importance of document clustering techniques. Although various document-clustering techniques have been studied in recent years, clustering quality still remains an area of concern. Particularly, majority of the present document clustering methods do not account for the semantic relationships and as a result give unsatisfactory clustering results. Semantic relationships consider the context of the usage of the term and do not solely rely on its isolated meaning. In the recent years, a lot of effort has gone into applying semantics to document clustering. This paper presents a survey of various research papers that have been studied and highlights the merits and demerits of each clustering algorithm. This will give a direction to future research in a more focused manner.