No abstract

No abstract

Internet and social media platforms such as Twitter, Facebook, and several blogs provide various types of helpful information worldwide. The increased usage of social media and e-commerce websites is constantly generating a massive volume of data about image/video, sound, text, etc. The text among these is the most significant type of unstructured data, requiring special attention from researchers to acquire meaningful information. Recently, many techniques have been proposed to obtain insights from these data. However, there are still challenges in dealing with the text of enormous size; therefore, accurate polarity detection of consumer reviews is an ongoing and exciting problem. Due to this, it is challenging to derive exact meanings from the textual data from consumer reviews, comments, tweets, posts, etc. Previously, a reasonable amount of work has been conducted to simplify the extraction of exact meanings from these data. A unique technique that includes data gathering, preprocessing, feature encoding, and classification utilizing three long short-term memory variations is presented to address sentiment analysis problems. Analysing appropriate data collection, preprocessing, and classification is crucial when interpreting such data. Different textual datasets were used in the studies to gauge the importance of the suggested models. The proposed technique of predicting sentiments shows better, or at least comparable, results with less computational complexity. The outcome of this work shows the significant importance of sentiment analysis of consumer reviews and social media content to obtain meaningful insights.

Software Defined Networking (SDN), as a cutting-edge network, splits control and management planes from the data plane for simplifying network manageability as well as programmability. In SDN, network policies change with the passage of time due to changes in the application environment, topology or user/admin requirements. As a result, modifications at the control plane take place. In existing research works, packet violations occur due to already installed flow rules at the data plane (switches) that are not modified in case of a change of the Access Control List (ACL) policies at the SDN controller. There has been no research carried out that identifies packet violations and network inefficiencies in case of policy change. Our novel approach stores generated flow rules at the SDN controller and detects policy change, along with conflicting flow rules, to resolve the identified problem of policy change. Afterwards, the conflicting flow rules are removed from switches and new flow rules are installed along the new path according to new ACL policies. It helps to minimize packet violations, which increases network efficiency. In this research work, we deal with the inefficiencies of policy change detection with respect to access time, cost and space. In this regard, we used abstractions to formalize and detect network policies with the help of multi-attributed graphs. We utilized intent-based policies for the representation and implementation of our proposed approach. In addition, we used extended performance metrics for the analysis of our proposed approach. The simulation results show that our proposed approach performs better as compared to the existing approach, by varying the number of policy change and packet transmission rate. The results clearly indicate that our proposed approach helps to increase network performance and efficiency.