Sentimental Analysis on voice using AWS Comprehend

Sentimental Analysis on voice using AWS Comprehend

Table of Contents




Abstract

Sentimental analysis plays an important role in these days because many start-ups have started with user-driven content [1]. Sentiment analysis is an important research area in natural language processing. Natural language processing has a wide range of applications like voice recognition, machine translation, product review, aspect-oriented product analysis, sentiment analysis and text classification etc [2]. This process will improve the business by analyse the emotions of the conversation. In this project author going to perform sentimental analysis using Amazon Comprehend. Amazon Comprehend is a natural language processing (NLP) service that uses machine learning to extract the content of the document. By using this service can extract the unstructured data like images, voice etc. Thus, will identify the emotions of the conversation and give the output whether the conversation is Positive, Negative, Neutral, or Mixed. To perform this author going to use some services from Aws like s3 which is used for the data store, Transcribe which is used for converting the audio to text, Aws Glue is used to generate the metadata from the comprehend file, Aws Comprehend is used to generate the sentiment file from the audio, Lambda is used to trigger from the data store s3, Aws Athena is used to convert text into structured data and finally there is quick sight where he can visualize the data from the given file.

  • Author Keywords

    • Sentimental analysis ,
    • NLP ,
    • S3 ,
    • Transcribe ,
    • Aws Glue ,
    • Aws Comprehend ,
    • Lambda ,
    • Aws Athena ,
    • Quick sight

Introduction

Nowadays knowing the people emotions is very important for the improvement of business and also for the analysis of the business. [7] people will have a different opinion on movies, political issues and also on products [8] The capability of detecting the sentiment of the speaker in the audio can serve two basic functions: (i) it can enhance the retrieval of the particular audio in question, thereby, increasing its utility, and (ii) the combined sentiment of a large number of audio on a similar topic can help in establishing the general sentiment. It is important to note that automatic sentiment detection using text is a mature area of research, and significant attention has been given to product reviews, we focus our attention on dual sentiment detection in videos based on audio and text analysis. Previously there was doing sentiment analysis only on structured data but nowadays as the growth of data is increased in social media is become more so sentiment analysis is performing on unstructured data and it is difficult to extract sentiment in the form of manual analysis is not an easy task.[7] There are different methods to find the sentimental analysis such as Naïve Bayes, super vector machine, and also other machine learning techniques like supervise and unsupervised learning used for classification of the test set. This machine learning technique can provide better results but it will take a lot of time to train the data set. [9]Traditional methods will not provide accurate sentiment results to solve real-time complexity this is only possible by doing the automation and make the work simple. In this project author is moving to cloud to provide many advantages such as time complexity can perform and also automation by using lambda and so on compared to a manual system and also can perform the automation for converting audio to text and also converting text to accurate sentiment and also provide good security and no one can break the security all the data will be encrypted. They can get the result in the form 4 ways whether the sentiment is positive, negative, neutral, and mixed. The author is going to use the cloud services like Identity Access Management (IAM) used for security purpose, AWS Comprehend Is used to generate the sentiment file, AWS Transcribe is used to convert the audio into text, AWS Athena is used to convert file to structured data, AWS Glue is used to generate the metadata, AWS Lambda is used to trigger the audio file from the data store, AWS Quick sight is used to visualize the data from the file. This will help to find the sentiment of the audio and provide the result in the form of dashboards like bar charts so it is easy for people to improve the business. These services will help to reduce the cost when compared with the normal systems and no need of writing code again and again once write and use number of times by using the lambda.

Conclusion

Collecting the audio files and finding the sentiment is used for the improvement of business as well they can analysis the business performance. To find sentiment results in this proposed system author is used some AWS services like Identity Access management is used for providing the security to the files. S3 is a data store where the author will upload the audio file and from that audio file, author can generate the transcribe file by using the service AWS Transcribe. This application can be used to analyze the various emotions of people in a different environments such as political campaigns, customer feedback, social media, and many.

About KSRA

The Kavian Scientific Research Association (KSRA) is a non-profit research organization to provide research / educational services in December 2013. The members of the community had formed a virtual group on the Viber social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.

KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.

Our main services Based on Education for all Spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.

The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.

FULL Paper PDF file:

Sentimental Analysis on voice using AWS Comprehend

Bibliography

author

G. Satyanarayana, J. Bhuvana and M. Balamurugan,

Year

2020

Title

Sentimental Analysis on voice using AWS Comprehend

Publish in

2020 International Conference on Computer Communication and Informatics (ICCCI), Coimbatore, India, 2020, pp. 1-4,

Doi

10.1109/ICCCI48352.2020.9104105.

PDF reference and original file: Click here

+ posts

Somayeh Nosrati was born in 1982 in Tehran. She holds a Master's degree in artificial intelligence from Khatam University of Tehran.

Website | + posts

Professor Siavosh Kaviani was born in 1961 in Tehran. He had a professorship. He holds a Ph.D. in Software Engineering from the QL University of Software Development Methodology and an honorary Ph.D. from the University of Chelsea.

Website | + posts

Nasim Gazerani was born in 1983 in Arak. She holds a Master's degree in Software Engineering from UM University of Malaysia.