Opinion Mining or Sentiment Analysis is the process of mining emotions, attitudes, and opinions automatically from speech, text, and database sources through Natural Language Processing (NLP). Opinions can be given on anything. It may be a product, feature of a product or any sentiment view on a product. In this research, Mobile phone products reviews, fetched from Amazon.com, are mined to predict customer rating of the product based on its user reviews. This is performed by the sentiment classification of unlocked mobile reviews for the sake of opinion mining. Different opinion mining algorithms are used to identify the sentiments hidden in the reviews and comments for a specific unlocked mobile. Moreover, a performance analysis of Sentiment Classification algorithms is performed on the data set of mobile phone reviews. Results yields from this research provide the comparative analysis of eight different classifiers on the evaluation parameters of accuracy, recall, precision and F-measure. The Random Forest Classifiers offers more accurate predictions than others but LSTM and CNN also give better accuracy.

In cloud computing, requirements engineering is a greatly under-researched topic. Requirement elicitation is a key activity that helps in assemble the requirements of a system from different users, customers and stakeholders. Cloud services providers need methods to correctly elicit requirements from consumers, as the consumers of cloud services are more diverse and there occur some conflictions in the non-functional requirement of some kinds of consumers. Sometimes eliciting security requirements is an important task, because the cloud services are acquired by potential cloud consumers are secure for them to use. Both literature and market surveys are performed on different elicitation approaches that are followed by CSPs to fetch consumer requirements, recommendations and data from cloud service providers and from consumers of cloud computing services. This study aims to discuss the elicitation methods being used by cloud providers in Pakistan IT industry, and the resulting feedback of the consumers by these methods. This would lead to determine current elicitation methods are sufficient or there is a need to design a new elicitation method that can sufficiently provide with more customer satisfaction. We have used semi-structured interviews and questionnaires to gather information about the elicitation techniques that are used by cloud providers to elicit consumer requirements. This study is conducted in Pakistan IT industry. Somehow, this research enlightens the trend and scope of cloud computing in Pakistan. This study would be beneficial for cloud providers adequately gather their consumer requirements and enhance the knowledge of elicitation techniques that are used by cloud providers.