Blockchain Leveraged Cyberbullying Preventing framework

The popularity of social media has exploded worldwide over the last few decades and becomes the most preferred mode of social interaction. The internet also provides a new platform through which adolescents are being bullied. Appropriate means of cyberbullying detection is still partial and in some cases very limited. Moreover, research on cyberbullying detection extensively focuses on surveys and its psychological impacts on victims. However, prevention has not been widely addressed. To bridge the gap, this paper aims to detect cyberbullying efficiently. This paper employs a standard machine learning method and natural language processing technique as a part of the detection process in decentralized Blockchain leveraged architecture. We provide a fog based architecture for cyberbullying detection, aiming at relieving the server's load by placing the detection and the prevention of cyberbullying processes at the fog layer. The proposal might offer a probable solution to save users, particularly adolescents from severe consequences of cyberbullying.

Sarcasm Detection in Text Data Using Glove Embedding

Sarcasm is a way of expressing feelings in which people say or write something which is completely different or opposite to what they actually mean to say. Hence it is very difficult to identify sarcasm . It is usually an ironic or satirical remark tempered by humor. Mainly, people use it to say the opposite of what's true to make someone look or feel foolish. Understanding the sarcasm can improve the accuracy of sentiment analysis. Sentiment analysis (or opinion mining) is a natural language processing technique used to determine whether data is positive, negative or neutral. This helps in identifying what the opinions of users or individual or society are. In this project an attempt is made to develop a model to detect if a sentence is sarcastic or if it is not sarcastic. Keywords: Sarcasm detection, GloVe Embedding, LSTM, Natural Language Processing, Sentiment

Toward travel pattern aware tourism region planning: a big data approach

Purpose The purpose of this paper is to propose and demonstrate how Tourism2vec, an adaptation of a natural language processing technique Word2vec, can serve as a tool to investigate tourism spatio-temporal behavior and quantifying tourism dynamics. Design/methodology/approach Tourism2vec, the proposed destination-tourist embedding model that learns from tourist spatio-temporal behavior is introduced, assessed and applied. Mobile positioning data from international tourists visiting Tuscany are used to construct travel itineraries, which are subsequently analyzed by applying the proposed algorithm. Locations and tourist types are then clustered according to travel patterns. Findings Municipalities that are similar in terms of their scores of their neural embeddings tend to have a greater number of attractions than those geographically close. Moreover, clusters of municipalities obtained from the K-means algorithm do not entirely align with the provincial administrative segmentation.

Food Reviews Classification using multi-label convolutional neural network text classifier

Most commercial websites, such as Amazon, encourage users to leave reviews of the goods and services they get after purchasing them. For certain consumers, this analysis is critical when determining whether or not to buy a product. Understanding the consequences of feedback and correctly classifying their utility may therefore be an advantageous method for websites. The classification results can also be used as a review and recommendation program for ongoing success. Nowadays people visit several restaurants on various occasions. They get confused most of the time after having a look at the food menu. Based on the ratings and reviews of the dish it becomes easier for them to decide the dish they wish to order. However they unable to read each review of the previous customers. So to overcome this issue, we have proposed NLP (Natural Language Processing) technique and Spacy CNN (Convolutional Neural Network) pipeline system which will classify all the reviews in a single rating. Each review is labelled with a reviewer's score indicating the sentiment of the reviewers. Our task is to predict a reviewer’s score on a scale of 0 or 1. Where 1 indicates the users like the dish while 0 indicates that the reviewers were not satisfied with the dish.