Presentation from Penn State's Nittany Watson Challenge Immersion event on January 19-20, 2017.
Student examples include choosing classes, searching clubs, selecting professors etc… Administration examples include evaluating investments, curriculum effectiveness, etc...
The Alchemy API segment will provide hands-on experience and example usage of two Alchemy API services on Bluemix: AlchemyData News and AlchemyLanguage services.
Examples of the use of Alchemy API include AlchemyData News which indexes 250k to 300k English language news and blog articles every day with historical search available for the past 60 days. The system enables developers to query the News API directly without needing to crawl, enrich, store the data themselves. Go beyond simple keyword based searches with AlchemyData News.
AlchemyLanguage uses one or all of the natural language processing APIs available through AlchemyLanguage to analyze your content and add high-level semantic information - such as keywords, sentiment or concepts - to create smart applications
4. ™
Tradeoff Analytics help people weigh their options and make the
right choices.
+ +
Narrow down to the
best options to meet
multiple goals
Explore visually
Recommend based on
the preferred choices
+
5. Tradeoff Analytics is a Watson Cognitive Service on IBM
Watson Developer Cloud
Access the service on Watson developer Cloud at:
http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/tradeoff-analytics.html
Access the Public Wiki
Public WIKI: https://w3-connections.ibm.com/wikis/home?lang=en-
us#!/wiki/People%20Insights%20Services%20on%20WDC/page/Tradeoff%20Analytics
6. Three Pillars of the Tradeoff Analytics Technology
Applying mathematical models to narrow
down the number of choices to only the
superior alternatives
Applied Mathematics
Facilitates results interpretation in a
consumable and interactive manner
Visual Analytics
Provides breakthrough tools that can help
guide the decision maker through the
decision process, recommends preferred
options, and analyzes and highlights
decision tradeoffs.
Cognition
7. What does Tradeoff Analytics do?
The IBM Watson™ Tradeoff Analytics service helps people make better choices by:
1) Using mathematical filtering techniques to identify the top options based on multiple
criteria
2) Helping decision makers explore the tradeoffs between options when making
complex decisions.
3) Combining smart visualization and analytical recommendations for easy and intuitive
exploration of tradeoffs.
4) Filtering out less attractive options based on a user’s specified objectives,
preferences, and priorities
5) Encourage the user's exploration of the remaining optimal candidates
6) Helps decision makers consider only the goals that matter most and only the best
options to make a final, informed decision.
7
Tradeoff Analytics helps people make better choices while taking into account multiple,
often conflicting, goals that matter when making that choice.
15. 15
Key Capabilities
Concept Tagging: high-level concepts in text (e.g. this article is about monetary policy)
Taxonomy Classifier: hierarchical categorization (finance/personal finance/credit card)
Entity Extraction: what are the entities (people, places, organizations, etc.) in text
Sentiment Analysis: how are people talking about the entities (positive, negative)
Emotion Analysis: what emotions are people expressing (joy, fear, sadness, anger, disgust)
Linked Data Support: appending additional information about the entity
Microformats Parsing: semantic information embedded in the article
Text Extraction: extract the important parts of text within an article
Relation Extraction: subject / action relations between entities
Language Detection: what language is this written in
Feed Detection: find the RSS feeds in the website
Keyword Extraction: important topics in content
Author Extraction: who wrote the article
AlchemyLanguage supports the following features: