Scribd
Upload
34 views

Text Analysis: Chapter 03: Sentiment Analysis With SAP HANA

Uploaded by

florencia
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
34 views

Text Analysis: Chapter 03: Sentiment Analysis With SAP HANA

Uploaded by

florencia
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

• Text Analysis

Chapter 03: Sentiment Analysis with SAP HANA

© © 2016 SAP UCC Magdeburg. All rights reserved. 1


• Definitions

• What is a sentiment?
 Subjective impressions, not facts
 Attitudes, opinions, emotions
 For / against, like / dislike, good / bad, etc.
• What is Sentiment Analysis?
 The automated extraction of subjective content from digital text and predicting the
subjectivity as positive or negative
 Analyze people‘s opinions, attitudes etc. towards entities and their attributes expressed
in written text
 Entities can be products, services, organizations, events, issues, topics and much more

Sources: [1]

© © 2016 SAP UCC Magdeburg. All rights reserved. 2


• Twitter terminology: real-life example

© © 2016 SAP UCC Magdeburg. All rights reserved. 3


• Sentiment examples

positive

neutral

negative

© © 2016 SAP UCC Magdeburg. All rights reserved. 4


• Use Cases

• Business Applications
• Politics
• Recommender System
• Expert Finding
• Summarization
• Government Intelligence

Sources: [2]

© © 2016 SAP UCC Magdeburg. All rights reserved. 5


• Impact of Sentiment Analysis

• Why is Sentiment Analysis important?


 Opinion of mass is important
 A company wants to find out reviews of its products
 As a tool to improve marketing strategy
• Questions asked through Sentiment Analysis:
 Is this product review positive or negative?
 Based on a sample of tweets, how are people responding to this ad campaign/product
release/news item?

© © 2016 SAP UCC Magdeburg. All rights reserved. 6


• Sentiment Analysis in SAP HANA - Process

Sources: [2]

© © 2016 SAP UCC Magdeburg. All rights reserved. 7


• Sentiment Analysis in SAP HANA - Process

• Subjectivity Classification
 Opinion
 View
 Belief
 Sentiment

Sources: [2]

© © 2016 SAP UCC Magdeburg. All rights reserved. 8


• Sentiment Analysis in SAP HANA - Process

• Sentiment Classification
1. Find positive/negative keywords with topics
2. Find positive/negative keywords with negation/intensifier
3. In SAP HANA the output for keyword/topic/modifier combination is done in 7 sentiment
levels:
o Strong/Weak + Positive
o Strong/Weak + Negative or
o Neutral or Minor/Major Problem

Sources: [3]

© © 2016 SAP UCC Magdeburg. All rights reserved. 9


Sources
 [1]
B. Liu, Sentiment Analysis: Mining Opinions, Sentiments, and Emotions. Cambridge University Press: 2015.
 A. Kumar, T. M. Sebastian, “Sentiment Analysis: A Perspective on its Past. Present and Future,” International Journal of
[2]

Intelligent Systems and Applications, vol. 4, no. 10, 2012, http://www.mecs-press.org/ijisa/ijisa-v4-n10/IJISA-V4-N10-


1.pdf.
 SAP SE (Nov. 2014). “SAP HANA SPS 09 - What’s New? Text Analysis,“ hcp.sap.com. [Online]. Available:
[3]

https://hcp.sap.com/content/dam/website/saphana/en_us/Technology%20Documents/SPS09/SAP%20HANA%20SPS
%2009%20-%20Text%20Analysis.pdf. [Accessed: Aug. 31, 2016].
 SAP SE (May 11, 2016). “SAP HANA Text Analysis Developer Guide,” help.sap.com. [Online]. Available:
[4]

http://help.sap.com/hana/SAP_HANA_Text_Analysis_Developer_Guide_en.pdf. [Accessed: Aug. 31, 2016].

© © 2016 SAP UCC Magdeburg. All rights reserved. 10

You might also like