This document discusses using big data analytics for social media sentiment analysis. It proposes building a prototype tool to analyze sentiment trends on Twitter for a company's marketing campaign. The tool would use supervised machine learning to classify tweets as positive or negative sentiment and visualize the trend over time. This case study aims to demonstrate how social media analytics can provide useful insights for various phases of a marketing campaign's lifecycle in a cost-effective manner using cloud computing technologies.
Adaptation of the technology of the static code analyzer for developing paral...PVS-Studio
In the article the question of use of the static code analyzers in modern parallel program development processes is considered. Having appeared in 70-80s as an addition to compilers, the static analyzers stopped to be popular with the developers in 90s. The reason was probably the increase of the errors diagnostics quality by the compilers. But in 2000s the interest to the static code analyzers started to increase again. It is explained by the fact that new static code analyzers were created, which started to detect quite difficult errors in programs. If the static code analyzers of the past made it possible, for example, to detect an uninitialized variable, modern static code analyzers tend to detect an unsafe access to data from several threads. The modern tendency of static code analyzers development became their use for diagnosing errors in parallel programs. In the work the situations are considered, where the use of such tools makes it possible to considerably simplify the process of creating parallel program solutions.
This is one of the estimation methodologies called 'MVC points' that was created to estimate J2EE and .Net applications. I have uploaded a .ppt file for the same also and this is a full paper.
I have been working on a new breed of estimation methodologies called "Open estimation methodologies". They can be called "Deliverable based estimation methodologies" also. This presentation is about this family of methodologies.
Review on Algorithmic and Non Algorithmic Software Cost Estimation Techniquesijtsrd
Effective software cost estimation is the most challenging and important activities in software development. Developers want a simple and accurate method of efforts estimation. Estimation of the cost before starting of work is a prediction and prediction always not accurate. Software effort estimation is a very critical task in the software engineering and to control quality and efficiency a suitable estimation technique is crucial. This paper gives a review of various available software effort estimation methods, mainly focus on the algorithmic model and non algorithmic model. These existing methods for software cost estimation are illustrated and their aspect will be discussed. No single technique is best for all situations, and thus a careful comparison of the results of several approaches is most likely to produce realistic estimation. This paper provides a detailed overview of existing software cost estimation models and techniques. This paper presents the strength and weakness of various cost estimation methods. This paper focuses on some of the relevant reasons that cause inaccurate estimation. Pa Pa Win | War War Myint | Hlaing Phyu Phyu Mon | Seint Wint Thu "Review on Algorithmic and Non-Algorithmic Software Cost Estimation Techniques" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-5 , August 2019, URL: https://www.ijtsrd.com/papers/ijtsrd26511.pdfPaper URL: https://www.ijtsrd.com/engineering/-/26511/review-on-algorithmic-and-non-algorithmic-software-cost-estimation-techniques/pa-pa-win
Adaptation of the technology of the static code analyzer for developing paral...PVS-Studio
In the article the question of use of the static code analyzers in modern parallel program development processes is considered. Having appeared in 70-80s as an addition to compilers, the static analyzers stopped to be popular with the developers in 90s. The reason was probably the increase of the errors diagnostics quality by the compilers. But in 2000s the interest to the static code analyzers started to increase again. It is explained by the fact that new static code analyzers were created, which started to detect quite difficult errors in programs. If the static code analyzers of the past made it possible, for example, to detect an uninitialized variable, modern static code analyzers tend to detect an unsafe access to data from several threads. The modern tendency of static code analyzers development became their use for diagnosing errors in parallel programs. In the work the situations are considered, where the use of such tools makes it possible to considerably simplify the process of creating parallel program solutions.
This is one of the estimation methodologies called 'MVC points' that was created to estimate J2EE and .Net applications. I have uploaded a .ppt file for the same also and this is a full paper.
I have been working on a new breed of estimation methodologies called "Open estimation methodologies". They can be called "Deliverable based estimation methodologies" also. This presentation is about this family of methodologies.
Review on Algorithmic and Non Algorithmic Software Cost Estimation Techniquesijtsrd
Effective software cost estimation is the most challenging and important activities in software development. Developers want a simple and accurate method of efforts estimation. Estimation of the cost before starting of work is a prediction and prediction always not accurate. Software effort estimation is a very critical task in the software engineering and to control quality and efficiency a suitable estimation technique is crucial. This paper gives a review of various available software effort estimation methods, mainly focus on the algorithmic model and non algorithmic model. These existing methods for software cost estimation are illustrated and their aspect will be discussed. No single technique is best for all situations, and thus a careful comparison of the results of several approaches is most likely to produce realistic estimation. This paper provides a detailed overview of existing software cost estimation models and techniques. This paper presents the strength and weakness of various cost estimation methods. This paper focuses on some of the relevant reasons that cause inaccurate estimation. Pa Pa Win | War War Myint | Hlaing Phyu Phyu Mon | Seint Wint Thu "Review on Algorithmic and Non-Algorithmic Software Cost Estimation Techniques" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-5 , August 2019, URL: https://www.ijtsrd.com/papers/ijtsrd26511.pdfPaper URL: https://www.ijtsrd.com/engineering/-/26511/review-on-algorithmic-and-non-algorithmic-software-cost-estimation-techniques/pa-pa-win
SentiTweet is a sentiment analysis tool for identifying the sentiment of the tweets as positive, negative and neutral.SentiTweet comes to rescue to find the sentiment of a single tweet or a set of tweets. Not only that it also enables you to find out the sentiment of the entire tweet or specific phrases of the tweet.
Make a query regarding a topic of interest and come to know the sentiment for the day in pie-chart or for the week in form of line-chart for the tweets gathered from twitter.com
Want to learn data analytics or just grab the information about data analytics and its future? https://coursedekho.com/data-analytics-courses-in-surat/
The significance of Data Science has impressively increased over recent years. The contemporary period is the intersection of data analytics with emerging technologies that involve artificial intelligence (AI), machine learning (MI), and automation. And these three things have an ocean of career opportunities. In this post, I am sharing with you some best Data Analytics Courses in Surat, with a detailed course curriculum and placements guarantee.
#education
#data
#DataAnalytics
#DataScience
#DataCourse
#AnalyticsCourses
#AnalyticsCourse
#DataScienceCourse
#DataScienceCourses
#CoursesInIndia
#DataJob
Citihub Open Source and Cloud approach to Social Media ListeningChris Allison
Citihub Consulting discusses open, flexible technology solutions for Social Listening based on open source technologies running on public cloud platforms.
SentiTweet is a sentiment analysis tool for identifying the sentiment of the tweets as positive, negative and neutral.SentiTweet comes to rescue to find the sentiment of a single tweet or a set of tweets. Not only that it also enables you to find out the sentiment of the entire tweet or specific phrases of the tweet.
Make a query regarding a topic of interest and come to know the sentiment for the day in pie-chart or for the week in form of line-chart for the tweets gathered from twitter.com
Want to learn data analytics or just grab the information about data analytics and its future? https://coursedekho.com/data-analytics-courses-in-surat/
The significance of Data Science has impressively increased over recent years. The contemporary period is the intersection of data analytics with emerging technologies that involve artificial intelligence (AI), machine learning (MI), and automation. And these three things have an ocean of career opportunities. In this post, I am sharing with you some best Data Analytics Courses in Surat, with a detailed course curriculum and placements guarantee.
#education
#data
#DataAnalytics
#DataScience
#DataCourse
#AnalyticsCourses
#AnalyticsCourse
#DataScienceCourse
#DataScienceCourses
#CoursesInIndia
#DataJob
Citihub Open Source and Cloud approach to Social Media ListeningChris Allison
Citihub Consulting discusses open, flexible technology solutions for Social Listening based on open source technologies running on public cloud platforms.
The world has witnessed explosive digital growth in the last two decades, which has led to a data deluge. This data may be
holding some key business insights or solutions to crucial problems. Data Science is the key that unlocks this possibility
to extract vital insights from the raw digital data. These findings can then be visualized, and communicated to the
decision-makers to be acted upon.Online Data Science Training is the best choice for the students to begin a new life. We
provide Data Science Training and Placement for the students .
Enterprise Project Management Essential #3Nah Wee Yang
The third series of popular "Enterprise Project Management Essential" seminar organized by "The Project Expert" Systemethod, sponsored by Microsoft Singapore, in 2008. Topics including: Using SharePoint in Project Management, and EPM Implementation 101.
Data science training in hyd ppt converted (1)SayyedYusufali
Data Science Online Training In HA comprehensive up-to-date Data Science course that includes all the essential topics of the Data Science domain, presented in a well-thought-out structure.
Taught and developed by experienced and certified data professionals, the course goes right from collecting raw digital data to presenting it visually. Suitable for those with computer backgrounds, analytic mindset, and coding knowledge.hyderabad Data Science Online Training
#datascienceonlinetraininginhyderabad
#datascienceonline
#datascienceonlinetraining
#datascience
Data science training in hyd pdf converted (1)SayyedYusufali
Overview of Data Science Courses Online
A comprehensive up-to-date Data Science course that includes all the essential topics of the Data Science domain, presented in a well-thought-out structure.
Taught and developed by experienced and certified data professionals, the course goes right from collecting raw digital data to presenting it visually. Suitable for those with computer backgrounds, analytic mindset, and coding knowledge.
What You'll Learn In Data Science Courses Online
Grasp the key fundamentals of data science, coding, and machine learning. Develop mastery over essential analytic tools like R, Python, SQL, and more.
Comprehend the crucial steps required to solve real-world data problems and get familiar with the methodology to think and work like a Data Scientist.
Learn to collect, clean, and analyze big data with R. Understand how to employ appropriate modeling and methods of analytics to extract meaningful data for decision making.
Implement clustering methodology, an unsupervised learning method, and a deep neural network (a supervised learning method).
Build a data analysis pipeline, from collection to analysis to presenting data visually.
#datasciencecoursesonline
#datascience
#datasciencecourses
Data science training in hydpdf converted (1)SayyedYusufali
Best Tableau Training Institute In Hyderabad is a robust growing data visualization tool that is used in the Business Intelligence Industry. EduXFactor Training helps you to simplify raw data in a straightforward format. The data Analysis is high-speed tracking with Tableau tool presenting creations in dashboards and worksheets
This course welcomes anyone who are passionate about playing around with data, regardless of technical or analytical background. Users can create and distribute interactive & sharable dashboards that depict the large data into easily readable graphs and charts.
EduXFactor Tableau course is exclusively designed to help you to learn, practice & explore various tools. This certification will be a stepping -stone to your Business Intelligence journey. Through the entire course, you will get an opportunity to work on varied Tableau active projects Best Tableau Training Institute In Hyderabad
#besttableautraininginstituteinhyderabad
#besttableautraininginstitute
#besttableautraining
1. 1
Cork Institute of Technology - Candidate for Master of Science Degree 1
Using Big Data Analytics in a Social
Domain
Master’s in Cloud Computing 2013/2014
Ahmed Abdel-Aziz
May 2015
EMCCAe, CISSP, PMP
2. Cork Institute of Technology - Candidate for Master of Science Degree 2
Objective
1) Social Media, Analytics and the Marketing Campaign
2) Sentiment Analysis – Methodology & Techniques
3) The Need for Case-Study & an Analytics Prototype
4) Learning Outcomes & Future Work
3. Cork Institute of Technology - Candidate for Master of Science Degree 3
Social Media & Social Analytics
• Social media sites offspring of Web 2.0 Movement – Based
on cloud computing model (Software-as-a-Service)
• Percentage of companies using social media for marketing is
88%
Section 1 of 4
4. Cork Institute of Technology - Candidate for Master of Science Degree 4
Marketing Campaign Lifecycle
Section 1 of 4
• Consists of 5 phases
• Social analytics answers
social questions for each
phase
Ex: What is sentiment trend?
5. Cork Institute of Technology - Candidate for Master of Science Degree 5
• Social analytic projects based on sentiment analysis
benefit from a well thought out methodology
Section 2 of 4
Sentiment Analysis Methodology &
Techniques
6. Cork Institute of Technology - Candidate for Master of Science Degree 6
Section 2 of 4
Sentiment Analysis Methodology &
Techniques
• Social sentiment analysis starts with social listening
– Social listening can be performed using a variety of
open source tools such as PostgreSQL, R, Wordle,
and Circos, as well as tools such as Attensity 360 and
Analyze.
• Social data comes from 3 main categories of sources
– Social user’s account – analytic capability limited by social
media provider (FB, Twitter, LinkedIn)
– Social APIs – social media provider offers API to tap into
social data. Allows development of unique analytic programs
– 3rd party tools – provides very fast results but does not
offer same level of analytic capability of a custom program
7. SANS Technology Institute - Candidate for Master of Science Degree 7
Section 2 of 4
Sentiment Analysis Methodology
& Techniques
• Sentiment analysis techniques grouped into two main
categories:
• Supervised machine learning method
• Unsupervised method
• Supervised learning method learns features/words that
correlate with +ve/-ve sentiment. Can identify new text
sentiment
• Unsupervised methods a lexicon is used with words pre-
scored for polarity values. Sum of scores gives sentiment
• Both techniques widely used and offer comparable results
Cork Institute of Technology - Candidate for Master of Science Degree 7
8. Cork Institute of Technology - Candidate for Master of Science Degree 8
• Company launched new product to market – Marketing
campaign already launched long ago and in Account
Performance Phase
• Marketing team needs to measure upticks in sentiment
trend regarding new product to take appropriate actions
• Data science team believes continuous user surveys are
ineffective and a computational approach is necessary ->
Better results and much less intrusive
Need for Case-Study/Analytics Prototype
Section 3 of 4
9. Cork Institute of Technology - Candidate for Master of Science Degree 9
Need for Case-Study/Analytics Prototype
• Decision made to build a prototype for tool to measure
sentiment trend on Twitter specifically as start
• Twitter found to be the social network of choice regarding
brand and product sentiment topics à Thus Twitter
• Data science team key objectives:
– Produce useful results quickly and cost efficiently
Cloud Computing Value Proposition!?
– Get buy-in from marketing management to build full App
Section 3 of 4
10. Cork Institute of Technology - Candidate for Master of Science Degree 10
• Applying the Analytic Project Lifecycle to the Prototype
– Data Preparation
Input Data: raw tweets
Output Data: clean tweet text ready for sentiment analysis
– Analytic Model Planning & Building
Input Data: clean tweet text and learnt Naïve Bayesian model
Output Data: sentiment of analyzed tweets
– Communicate Results
Input Data: sentiment of analyzed tweets and tweets
Output Data: sentiment trend graph for both +ve and –ve
sentiments
Section 3 of 4
Need for Case-Study/Analytics Prototype
11. Cork Institute of Technology - Candidate for Master of Science Degree 11
Need for Case-Study/Analytics Prototype
Section 3 of 4
• Technology decisions made by data science team
– R programming language for social listening
– Twitter Social APIs for source of social data
– Leverage ready-made R packages to accelerate building time
– R programming for data preparation
– Leverage analytics cloud services offered such as Datumbox –
supervised machine learning method using Naïve Bayesian
– R programming to build main body for prototype analytics
application
– Making use of R plotting capabilities to present easy to understand
results for non-technical members of Marketing team
– Settling on the technologies to use to build the full blown
application dealing with much larger data sets – GPText/Pivotal HD
12. Cork Institute of Technology - Candidate for Master of Science Degree 12
Need for Case-Study/Analytics Prototype
Section 3 of 4
• Snippet R code for analytics application – Main Loop
• > possentiments = 0
• > negsentiments = 0
• > for (i in 1:"5")
• > {
• > tweets = searchTwitter("iPhone", n=5, lang="en”)t
• > tweet_txt = sapply(tweets, function(x) x$getText())
• > tweet_clean = clean.text(tweet_txt)
• > tweet_num = length(tweet_clean)
• ……..
• > for (i in 1:tweet_num)
• > {
• > tmp = getSentiment(tweet_clean[i], "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa")
• > tweet_df$sentiment[i] = tmp$sentiment
• ………..
• > }
• > possentiments <- c(possentiments, sum(tweet_df$sentiment=="positive"))
• > negsentiments <- c(negsentiments, sum(tweet_df$sentiment=="negative"))
• > Sys.sleep(5)
13. Cork Institute of Technology - Candidate for Master of Science Degree 13
Need for Case-Study/Analytics Prototype
• Plotting the trend of both positive and negative sentiments
Section 3 of 4
14. SANS Technology Institute - Candidate for Master of Science Degree 14
Learning Outcomes
• Initial State
– Good foundation in cloud computing and data analytics
– Very little knowledge in social domain – Not even FB account J
– Last coding experience was Java 13 years back
• Initial research project stages
– Social media university
– Addictive analytics workshop -> Introduction to Marketing domain
– Pivotal workshop to learn data analytics in social domain ->
Relevant Pivotal Data Analytics Platforms: GPText and Pivotal HD
• Later research project stages – practical
– Learning enough about R to build small scale analytics application
– How to leverage Datumbox analytics-as-a-service offering
Section 4 of 4
Cork Institute of Technology - Candidate for Master of Science Degree 14
15. Cork Institute of Technology - Candidate for Master of Science Degree 15
Summary
• Cloud, social, and Data Analytics synergy serve Marketing
• Is there an uptick in +ve/-ve sentiments of my product?
Is a question strategically important in the Account
Performance phase of a Marketing Campaign
• The research answered the question using a computational
approach based on a supervised learning method for
sentiment analysis that is cloud based
• Data source and data analytics in the cloud. Data preparation
and data presentation on-premise using R. Future work:
Optimize & Tune for Large Datasets -> Can be all Cloud