The Combined Power of Sentiment
Analysis and Personality Insights
Housekeeping Items
• Webinar widgets
• Ask your questions throughout the
presentation
• Twitter - #BuildingWithWatson, @IBMWatson
• Follow up
• Webinar slides, live recording and
additional resources
Our Expert: Zach Walchuk
Developer Evangelist, Watson
Developer Cloud
The housekeeping items
• Webinar slides, recording and Q&A will be emailed
• Enter questions in chat on webinar panel
• Or ask your questions on Twitter @IBMWatson
• Use #BuildingWithWatson
What will be covered today?
• Approaches to sentiment analysis
• Watson Personality Insights: The Big 5
• Sample calls
• Parameter explanation
• Document-­level,  entity-­targeted,  and  keyword-­targeted  sentiment  mining.
• Understands  negations,  amplifiers,  diminishers,  typos,  hashtags and  slang.
• Examples:
– Overall  Text  Sentiment
• So  happy  I  found  this  pizza
– Targeted  Sentiment
• So  happy  I  found  this  pizza,  I  really  don't  like  hot  dogs
Extract  positive  and  negative  opinions  from  any  text.
Sentiment Analysis
Watson Personality Insights: The Big 5
• Agreeableness
• A person's tendency to be compassionate and cooperative toward others
• Conscientiousness
• A person's tendency to act in an organized or thoughtful way
• Extraversion
• A person's tendency to seek stimulation in the company of others
• Emotional Range
• The extent to which a person's emotions are sensitive to the
individual's environment
• Openness
• The extent to which a person is open to experiencing a variety of
activities
Watson Personality Insights: The Big 5
Making Sentiment Calls - cURL
curl
'http://access.alchemyapi.com/calls/text/TextGetTextSentiment?outputMode=json&text=That%20
pizza%20was%20delicious&apikey=YOUR_API_KEY'
{
"status": "OK",
"totalTransactions": "1",
"language": "english",
"docSentiment": {
"score": "0.660833",
"type": "positive"
}
}
Sentiment Parameters
#AlchemistHour
• url – url of text to be analyzed
• only used with endpoints URLGetTextSentiment and
URLGetTargetedSentiment
• text – text to be analyzed
• only used with endpoints TextGetTextSentiment and
TextGetTargetedSentiment
• target – target phrase
• apikey – your API key
• outputMode –xml, json
• jsonp – desired JSONP callback (requires json outputMode)
• showSourceText – whether to include the original 'source text' the
sentiment was extracted from
Additional info for Sentiment Analysis
• Maximum document size for HTML documents is 600kb. Remaining
text after HTML cleaning must be less than 50kb.
• Sentiment analysis is supported for eight languages: English,
Spanish, Italian, German, French, Portuguese, Swedish, and Russia
• If the sentiment target is not found, a "cannot-locate-keyphrase" error
response will be returned
Making Personality Insights Calls - cURL
curl -v -X POST -d @personality.txt -u USERNAME:PASSWORD -H "Accept-Language: en"
-H "Content-Type: text/plain" -H "Accept: application/json" "Content-Language: en"
"https://gateway.watsonplatform.net/personality-insights/api/v2/profile"
{
"id": "Openness",
"name": "Openness",
"category": "personality",
"percentage": 0.8925013538451143,
},
{
"id": "Conscientiousness",
"name": "Conscientiousness",
"category": "personality",
"percentage": 0.7348076938514495,
},
{
"id": "Extraversion",
"name": "Extraversion",
"category": "personality",
"percentage": 0.4771565706306179,
},
{
"id": "Agreeableness",
"name": "Agreeableness",
"category": "personality",
"percentage": 0.4130282366306227,
},
{
"id": "Neuroticism",
"name": "Emotional range",
"category": "personality",
"percentage": 0.09469501678631477,
}
Personality Insights Header Parameters
• Content-Type – text/plain, text/html, application/json
• Accept – application/json, text/csv
• Accept-Language – en (english response only)
• Content-Language – en, es (english or spanish input)
• include_raw - if true, will return a raw score for each characteristic in
addition to a normalized score
• headers – if true, column labels are returned with CSV response
Are you ready to get started?
• Get an AlchemyAPI key and sign up on Bluemix
• Download the Alchemy and Watson SDKs
• Check out the Getting Started Guides and WDC
Documentation for examples
• Ask me questions!
Q&A
• Look out for a follow up email with a copy of these slides, a recording of
the webinar, Q&A recap, and additional resources
• View and share this presentation on SlideShare
• Follow us for more webinars
What’s next?
Contact us
1-877-253-0308
wdc-dev@bg.vnet.ibm.com
www.alchemyapi.com
Thank you for attending!

The Combined Power of Sentiment Analysis and Personality Insights

  • 1.
    The Combined Powerof Sentiment Analysis and Personality Insights
  • 2.
    Housekeeping Items • Webinarwidgets • Ask your questions throughout the presentation • Twitter - #BuildingWithWatson, @IBMWatson • Follow up • Webinar slides, live recording and additional resources
  • 3.
    Our Expert: ZachWalchuk Developer Evangelist, Watson Developer Cloud
  • 4.
    The housekeeping items •Webinar slides, recording and Q&A will be emailed • Enter questions in chat on webinar panel • Or ask your questions on Twitter @IBMWatson • Use #BuildingWithWatson
  • 5.
    What will becovered today? • Approaches to sentiment analysis • Watson Personality Insights: The Big 5 • Sample calls • Parameter explanation
  • 6.
    • Document-­level,  entity-­targeted, and  keyword-­targeted  sentiment  mining. • Understands  negations,  amplifiers,  diminishers,  typos,  hashtags and  slang. • Examples: – Overall  Text  Sentiment • So  happy  I  found  this  pizza – Targeted  Sentiment • So  happy  I  found  this  pizza,  I  really  don't  like  hot  dogs Extract  positive  and  negative  opinions  from  any  text. Sentiment Analysis
  • 7.
    Watson Personality Insights:The Big 5 • Agreeableness • A person's tendency to be compassionate and cooperative toward others • Conscientiousness • A person's tendency to act in an organized or thoughtful way • Extraversion • A person's tendency to seek stimulation in the company of others • Emotional Range • The extent to which a person's emotions are sensitive to the individual's environment • Openness • The extent to which a person is open to experiencing a variety of activities
  • 8.
  • 9.
    Making Sentiment Calls- cURL curl 'http://access.alchemyapi.com/calls/text/TextGetTextSentiment?outputMode=json&text=That%20 pizza%20was%20delicious&apikey=YOUR_API_KEY' { "status": "OK", "totalTransactions": "1", "language": "english", "docSentiment": { "score": "0.660833", "type": "positive" } }
  • 10.
    Sentiment Parameters #AlchemistHour • url– url of text to be analyzed • only used with endpoints URLGetTextSentiment and URLGetTargetedSentiment • text – text to be analyzed • only used with endpoints TextGetTextSentiment and TextGetTargetedSentiment • target – target phrase • apikey – your API key • outputMode –xml, json • jsonp – desired JSONP callback (requires json outputMode) • showSourceText – whether to include the original 'source text' the sentiment was extracted from
  • 11.
    Additional info forSentiment Analysis • Maximum document size for HTML documents is 600kb. Remaining text after HTML cleaning must be less than 50kb. • Sentiment analysis is supported for eight languages: English, Spanish, Italian, German, French, Portuguese, Swedish, and Russia • If the sentiment target is not found, a "cannot-locate-keyphrase" error response will be returned
  • 12.
    Making Personality InsightsCalls - cURL curl -v -X POST -d @personality.txt -u USERNAME:PASSWORD -H "Accept-Language: en" -H "Content-Type: text/plain" -H "Accept: application/json" "Content-Language: en" "https://gateway.watsonplatform.net/personality-insights/api/v2/profile" { "id": "Openness", "name": "Openness", "category": "personality", "percentage": 0.8925013538451143, }, { "id": "Conscientiousness", "name": "Conscientiousness", "category": "personality", "percentage": 0.7348076938514495, }, { "id": "Extraversion", "name": "Extraversion", "category": "personality", "percentage": 0.4771565706306179, }, { "id": "Agreeableness", "name": "Agreeableness", "category": "personality", "percentage": 0.4130282366306227, }, { "id": "Neuroticism", "name": "Emotional range", "category": "personality", "percentage": 0.09469501678631477, }
  • 13.
    Personality Insights HeaderParameters • Content-Type – text/plain, text/html, application/json • Accept – application/json, text/csv • Accept-Language – en (english response only) • Content-Language – en, es (english or spanish input) • include_raw - if true, will return a raw score for each characteristic in addition to a normalized score • headers – if true, column labels are returned with CSV response
  • 14.
    Are you readyto get started? • Get an AlchemyAPI key and sign up on Bluemix • Download the Alchemy and Watson SDKs • Check out the Getting Started Guides and WDC Documentation for examples • Ask me questions!
  • 15.
  • 16.
    • Look outfor a follow up email with a copy of these slides, a recording of the webinar, Q&A recap, and additional resources • View and share this presentation on SlideShare • Follow us for more webinars What’s next?
  • 17.