Facebook recently deployed Facebook Messages, its first ever user-facing application built on the Apache Hadoop platform. Apache HBase is a database-like layer built on Hadoop designed to support billions of messages per day. This paper describes the reasons why Facebook chose Hadoop and HBase over other systems such as Apache Cassandra and Voldemort and discusses the applicationBs requirements for consistency, availability, partition tolerance, data model and scalability. I explore the enhancements made to Hadoop to make it a more effective realtime system, the tradeoffs we made while configuring the system, and how this solution has significant advantages over the sharded MySQL database scheme used in other applications at Facebook and many other web-scalecompanies. I discuss the motivations behind my design choices, the challenges that we face in day-to-day operations, and future capabilities and improvements still under development.I offer these observations on the deployment as a model for other companies who are contemplating a Hadoop-based solution over traditional sharded RDBMS deployments.

/pdf/apache-hadoop-goes-realtime-at-facebook-25mf7o9ess.pdf

Apache Hadoop Goes Realtime at Facebook

Social media sentiment analysis (also known as opinion mining) which aims to extract people's opinions, attitudes and emotions from social networks has become a research hotspot. Conventional sentiment analysis concentrates primarily on the textual content. However, multimedia sentiment analysis has begun to receive attention since visual content such as images and videos is becoming a new medium for self-expression in social networks. In order to provide a reference for the researchers in this active area, we give an overview of this topic and describe the algorithms of sentiment analysis and opinion mining for social multimedia. Having conducted a brief review on textual sentiment analysis for social media, we present a comprehensive survey of visual sentiment analysis on the basis of a thorough investigation of the existing literature. We further give a summary of existing studies on multimodal sentiment analysis which combines multiple media channels. We finally summarize the existing benchmark datasets in this area, and discuss the future research trends and potential directions for multimedia sentiment analysis. This survey covers 100 articles during 2008---2018 and categorizes existing studies according to the approaches they adopt.

A survey on sentiment analysis and opinion mining for social multimedia

Multimodal sentiments have become the challenge for the researchers and are equally sophisticated for an appliance to understand. One of the studies that support MS problems is a MSA, which is the training of emotions, attitude, and opinion from the audiovisual format. This survey article covers the comprehensive overview of the last update in this field. Many recently proposed algorithms and various MSA applications are presented briefly in this survey. The article is categorized according to their contributions in the various MSA techniques. The main purpose of this survey is to provide a full image of the MSA opportunities and difficulties and related field with brief details. The main contribution of this article includes the sophisticated categorizations of a large number of recent articles and the illustration of the recent trend of research in the MSA and its related areas.

Multimodal Sentiment Analysis: A Survey and Comparison

In many network applications, Bloom filters are used to support exact-matching membership query for their randomized space-efficient data structure with a small probability of false answers. In this paper, we extend the standard Bloom filter to Locality-Sensitive Bloom Filter (LSBF) to provide Approximate Membership Query (AMQ) service. We achieve this by replacing uniform and independent hash functions with locality-sensitive hash functions. Such replacement makes the storage in LSBF to be locality sensitive. Meanwhile, LSBF is space efficient and query responsive by employing the Bloom filter design. In the design of the LSBF structure, we propose a bit vector to reduce False Positives (FP). The bit vector can verify multiple attributes belonging to one member. We also use an active overflowed scheme to significantly decrease False Negatives (FN). Rigorous theoretical analysis (e.g., on FP, FN, and space overhead) shows that the design of LSBF is space compact and can provide accurate response to approximate membership queries. We have implemented LSBF in a real distributed system to perform extensive experiments using real-world traces. Experimental results show that LSBF, compared with a baseline approach and other state-of-the-art work in the literature (SmartStore and LSB-tree), takes less time to respond AMQ and consumes much less storage space.

Networking - Locality-Sensitive Bloom Filter for Approximate Membership Query

A Novel Context-Aware Multimodal Framework for Persian Sentiment Analysis

Multimodal sentiment analysis is the analysis of emotions, attitude, and opinion from audiovisual format. A company can improve the quality of its product and services by analyzing the reviews about the product [5]. Sentiment analysis is widely used in managing customer relations. There are many textual reviews from which we cannot extract emotions by traditional sentiment analysis techniques. Some sentences in the textual reviews may derive deep emotions but do not contain any keyword to detect those emotions, so we used audiovisual reviews in order to detect emotions from the facial expressions of the customer. In this paper we take audiovisual input and extract emotions from video and audio in parallel from audiovisual input, finally classify the overall review as positive, negative or neutral based on the emotions detected.

Multimodal sentiment analysis: Sentiment analysis using audiovisual format

For faster access of data or in network bloom filter plays an important part in searching technique. It process data in short amount of time and frequently with probabilistic analysis. Bloom Filter also decreases the cost of analyzing data. Various applications are using this technology for accessing and processing the data. Thus by implementing Bloom's Filter over big data will result into efficient query accessing in big data. In this paper, an approach to implement Locality Sensitive Bloom Filter (LSBF) technique in big data is proposed. To remove the drawbacks of simple hashing technique, the LSBF must be implemented to store data in the bloom filter which will help to search the most approximate result by using the Locality Sensitive Hashing approach.

http://ieeexplore.ieee.org/iel7/7088896/7100186/07100483.pdf

Big data query optimization by using Locality Sensitive Bloom Filter

In recent time, HBase is growing with its requirement as data exploding in E-world. Hadoop provide distributed manner and taking technology to next level as it is using HBase to store bulk data. HBase works with Hadoop to transfer data to datanodes. As traditionally large file need to split for performing operations but MapReduce provide facility to do operations on single file. This paper providing concept to reduce traffic of data on network with efficient manner through probabilistic model of Bloom filter. Instead of taking whole data, Bloom filter is providing join operation only with array data structure by developing global filter.

Bloom filter based optimization on HBase with MapReduce

With fast pace growth in technology, we are getting more options for making better and optimized systems. For handling huge amount of data, scalable resources are required. In order to move data for computation, measurable amount of time is taken by the systems. Here comes the technology of Hadoop, which works on distributed file system. In this, huge amount of data is stored in distributed manner for computation. Many racks save data in blocks with characteristic of fault tolerance, having at least three copies of a block. Map Reduce framework use to handle all computation and produce result. Jobtracker and Tasktracker work with MapReduce and processed current as well as historical data that’s cost is calculated in this paper.

/pdf/cost-based-model-for-big-data-processing-with-hadoop-48bl6dmiel.pdf

Cost based Model for Big Data Processing with Hadoop Architecture

Cloud Computing is a platform that relies on sharing resources, software and information between remote servers and users over the network. Since cloud computing share distributed resources in open environment, it must be considered from privacy and security viewpoints. In this paper, we have discussed the security risks and concerns, key management, and mutual authentication of cloud computing. The paper also includes some models to tackle the challenges like regulatory, security and privacy to some extent. Next we discuss some solutions to mitigate these challenges along with a brief description on future work in cloud computing deployment.

https://ieeexplore.ieee.org/iel7/7370053/7380415/07380626.pdf

Mayank Bhushan

Papers

Multimodal sentiment analysis: Sentiment analysis using audiovisual format

Big data query optimization by using Locality Sensitive Bloom Filter

Bloom filter based optimization on HBase with MapReduce

Cost based Model for Big Data Processing with Hadoop Architecture

Identity management in hybrid cloud