Twitter is an online social networking service with more than 300 million users, generating a huge amount of information every day. Twitter's most important characteristic is its ability for users to tweet about events, situations, feelings, opinions, or even something totally new, in real time. Currently there are different workflows offering realtime data analysis for Twitter, presenting general processing over streaming data. This study will attempt to develop an analytical framework with the ability of in-memory processing to extract and analyze structured and unstructured Twitter data. The proposed framework includes data ingestion and stream processing and data visualization components with the Apache Kafka messaging system that is used to perform data ingestion task. Furthermore, Spark makes it possible to perform sophisticated data processing and machine learning algorithms in real time. We have conducted a case study on tweets about the earthquake in Japan and the reactions of people around the world with analysis on the time and origin of the tweets.

No abstract

Social networking sites (SNSs) like Facebook are widely used and have been broadly studied but despite years of investigation, accessibility complaints from individuals with visual impairments continue to persist. To investigate this issue we have conducted a quasi-ethnographic usability evaluation of Facebook involving blind participants, the mobile interface ( m.facebook.com ) and the JAWS screen reader on a desktop computer; a configuration that has been suggested in the related literature but insufficiently investigated. Six participants attempted 18 tasks designed to be representative of common SNS user activities. Of the features evaluated participants were most severely challenged by the process of creating a user profile and identifying other users with whom to establish relationships; two of the three core activities commonly viewed as characterizing SNSs. These findings suggest that despite recent progress additional research may be needed to make Facebook truly accessible for individuals with visual impairments.

No abstract

An essential prerequisite of an effective recommender system is providing helpful information regarding users and items to generate high-quality recommendations. Written customer review is a rich source of information that can offer insights into the recommender system. However, dealing with the customer feedback in text format, as unstructured data, is challenging. In this research, we extract those features from customer reviews and use them for similarity evaluation of the users and ultimately in recommendation generation. To do so, we developed a glossary of features for each product category and evaluated them for removing irrelevant terms using Latent Dirichlet Allocation. Then, we employed a deep neural network to extract deep features from the reviews-characteristics matrix to deal with sparsity, ambiguity, and redundancy. We applied matrix factorization as the collaborative filtering method to provide recommendations. As the experimental results on the Amazon.com dataset demonstrate, our methodology improves the performance of the recommender system by incorporating information from reviews and produces recommendations with higher quality in terms of rating prediction accuracy compared to the baseline methods.