This document summarizes a webinar about sentiment analysis and personality insights using Watson APIs. It discusses different approaches to sentiment analysis including document, entity and keyword targeting. It also describes the Big Five personality traits that the Personality Insights API analyzes. Examples are provided of API calls to conduct sentiment analysis and retrieve personality insights data. Parameters for the APIs and additional support information is also outlined.
2. Housekeeping Items
• Webinar widgets
• Ask your questions throughout the
presentation
• Twitter - #BuildingWithWatson, @IBMWatson
• Follow up
• Webinar slides, live recording and
additional resources
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 be covered 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
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 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
13. 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
14. 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!
16. • 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?