Sentiment analysis is similar to opinion mining, which is a popular research problem to search out in the field of NLP. Sentiment analysis determines the perspective of the author and identifies the positive, negative and neutral reviews. It provides the reviews or opinions of people's on text, article and product which can be positive, negative or neutral. Reviews on the different websites, social networking sites is an important source to collect the information regarding various brands of product and new features in technology (e.g. Windows, Mobiles). During the sentiment analysis various classification tools within the NLP are used to find out the positivity and negativity of reviews or comments. The paper presents a length aware hybrid approach to analyses the reviews either as positive or negative and present approach is tested on SuperFetch data set. The present approach is a combination of both supervised machine learning techniques that are Support Vector Machine and K-Nearest Neighbor in which SVM is working great for large size review and KNN is working best for small size review.

Change, in software requirements during its development phases, is considered as a major risk which may affect a software project to fail. Therefore, software engineering processes, methods, and tools are used in order to manage these risks whereas changes in requirements have many negative influences such as effects on system development life cycle (SDLC) phases, project progress, and outcome of a software project. Consequently, project managers must use risk management strategies, activities, and estimation techniques in order to manage and mitigate these risks which are caused due to changes in requirements. A novel model is proposed in this paper to manage and mitigate risks related to changing requirements. The proposed model is validated through qualitative research design. The results are in favor of the proposed model to show its effectiveness. It is anticipated that the proposed model will solve the problems of software companies in major to deal with risks about changing requirements.

A large number of people of a country uses public transport for their daily commute. Public transport users in a developed country get many facilities which is absent in a developing country like frequent transport, less traffic jam, maintaining time schedule, etc. In most of the developing countries, intercity public transports do not have any time schedule to arrive and leave in a stoppage and as a result, a person cannot manage his time accordingly which leads to waste valuable time. In this paper, we have proposed a system which is simple, cost-effective and will be able to save time for a public transport user that might be wasted due to bad timing. The system includes vehicle tracking system to trace the location of the transport and a website for the graphical view of the transport locations. A website has been developed with some dummy data to illustrate the proposed idea.

Online product reviews provide data about the user's perspective on the features that were experienced by them. Product features and corresponding opinions form a major part in analyzing the online product reviews. Extracting features from a huge number of reviews is classified into three major categories such as utilizing language rules, sequence labeling as well as the topic modeling. Latent Dirichlet Allocation (LDA) is one such topic model which clusters the document words into unsupervised learned topics using Dirichlet priors. The words so clustered are the features and opinion words in the product reviews domain. To identify appropriate product features from these clusters a hierarchical, domain independent Feature Ontology Tree (FOT) is applied to LDA clusters. The opinion bearing words of obtained product features are identified by utilizing the document indicators available from topic matrix of LDA. These indicators are useful to backtrack to the corresponding online review in which the product feature is present. The polarity of the opinion bearing word is calculated with the help of SentiWordNet. This improves the accuracy of the features using extracted LDA topic clusters and machine interpretation of polarity of opinion word is satisfactory.

Early diagnosis of a disease is a vital task in medical informatics. Data mining is one of the principal contributors in this discipline. Utilization of Data Mining Technology in Disease Forecasting System is a recognized trend and is successfully emerging in this domain. In today`s world, Heart Disease is the one of the most prevalent disease among people with a high mortality rate. It is essential to classify the reports of heart patients into correct subclasses to lower fatality rate. Over the years, Data mining classification and prediction approaches has been used extensively for disease prediction. This paper comes out with the compilation, analysis as well as comparative study of numerous classification approaches used for predictive analysis of several diseases. The goal of the survey is to provide a comprehensive review of the work done on disease prediction using different classification approaches in data mining.

The purpose of this study is to explore factors that influence practical work in chemistry for secondary schools in Wolaita Zone, Ethiopia. The study has identified teachers', learners' and school principals' perceptions to indicate the key factors that seem to inhibit the effective use of practical work in chemistry. The sample for the study comprised 56 chemistry teachers, 75 secondary school students, and 5 school principals. Data were collected using structured questionnaires, focus group discussion and interview. The collected data were analyzed using simple quantitative and qualitative analysis. The finding of the study revealed that factors that influencing practical work in chemistry of secondary schools are teachers' poor knowledge of practical work, full-time occupancy of chemistry teachers, absenteeism of the teacher at practical classes, late commencement of teaching a practical class; lack of awareness and motivation of school managements and unsafe working environments. Furthermore, lack of separate chemistry laboratory, lack of equipment in the laboratory, too short period allocated for practical work, low attitude students' toward practical work in chemistry, teachers' low level of expectation for the development of Information and communication technology (ICT) were the major factors that affect the practical work in chemistry. Finally, recommendations were forwarded based on the major finding in order to improve practical work in chemistry.

Automatic Speech Recognition presents natural phenomena for the communication among man and machine. The purpose of Speech Recognition speech system is to convert the sequence of sound units in the form of text description. The main objective of the research work is to develop the automatic spontaneous speech model for the Punjabi language. Punjabi is categorized as a constituent of the Indo-Aryan subgroup of the Indo-European family of languages. So far no work has been done in the field of spontaneous Punjabi speech recognition system. In spontaneous speech system, the sounds are usually unprompted and non- designed and are commonly described by repetitions, repairs, false start, partial words and non-planned words, silence gap etc. In this paper, the focus is on the development of the spontaneous speech model for the recognition of the Punjabi language. The GUI for Punjabi speech model also has been created and tested for the live Punjabi interview speech corpus. The recognition accuracy is 98.6% for Punjabi sentences and 98.8% for Punjabi words. The sphinx toolkit and java programming are used to build a spontaneous speech model for Punjabi live speech.

Institutional Ranking has become a common practice in higher educational institutions, and business schools are the most benefitted by such ranking announced worldwide based on various ranking criteria. The ranking is usually based on pedagogy, placement, research output, faculty-student ratio, international linkage, management of technology etc. In this paper, based on six postulates, we have argued and analysed why the performance of higher educational institutions should be based on sole criteria of Institutional Research Performance (IRP). We have developed a model of measuring research productivity for higher educational institutions based on calculating institutional research index and weighted research index. The institutional research productivity is calculated using a metric which consists of three institutional variables and one parameter. The three variables identified are the following: Number of Articles published in peer reviewed journals (A), Number of Books published (B), and Number of Case studies and/or Book Chapters (C) published during a given time of observation. The parameter used is a number of full-time Faculty members (F) which remains constant during a given period of observation. A framework for institutional ranking based on institutional research productivity by considering calculated Institutional Research Index is also developed which can be used to give grades to higher educational institutions. Further, the model is tested by making use of case example of two best Business Schools from the USA and two best Business Schools from India. The value of research index and weighted research index are calculated for these institutions and observed variation of research productivity during last four years is also studied and discussed.