A presentation at RubyConf in in Nashville, TN, USA by Ben Greenberg
“Without knowing the force of words, it is impossible to know more.” –Confucius “My dispatches are merely dry matter of fact and detail.” –Lawrence Gobright, Washington AP Chief (1856) @rabbigreenberg
What’s Love Got To Do With It? Ruby and Sentiment Analysis Ben Greenberg @rabbigreenberg
Who is talking right now? 🤔 (i.e. Hi! “) • I 💙 Ruby • Co-editor of Torah && Tech • Former rabbi & community organizer • 🌎 San Diego ↝ NYC ↝ Boston ↝ Denver ↝ NYC ↝ Tel Aviv 🌍 • Developer Advocate @ Nexmo @rabbigreenberg
Our Roadmap A. Why does this matter? B. What is sentiment analysis? C. What can I build with it? D. Let’s build it! E. Test Run @rabbigreenberg
Why does this matter? @rabbigreenberg
Language is not only a passive vehicle for information @rabbigreenberg
“Last night I had dinner with… someone, it was delicious“ ’’אתמול בערב אכלתי ארוחת ערב …עם היא, מישהי ’’טעיימה @rabbigreenberg
Language is a conduit constructor @rabbigreenberg
What is sentiment analysis? @rabbigreenberg
“ I believe that at the end of the century the use of words and general educated opinion will have altered so much that one will be able to speak of machines thinking without expecting to be contradicted. “ - Alan Turing, 1950 @rabbigreenberg
“Last night I had dinner with someone, it was delicious“ “sentiment”=>{“document”=>{“score”=>0.970908, “label”=>”positive”}} “semantic_roles”=>[{“subject”=>{“text”=>”I”}, “sentence”=>”Last night I had dinner with someone, and it was delicious.”, “object”=>{“text”=>”dinner”}, “action”=>{“verb”=>{“text”=>”have”, “tense”=>”past”}, “text”=>”had”, “normalized”=>”have”}}], “keywords”=>[{“text”=>”Last night”, “relevance”=>0.998604, “count”=>1}, {“text”=>”dinner”, “relevance”=>0.672861, “count”=>1}], “emotion”=>{“sadness”=>0.049938, “joy”=>0.857958, “fear”=>0.041413, “disgust”=>0.034346, “anger”=>0.025449}}}, “categories”=>[{“score”=>0.658246, “label”=>”/food and drink/food”, “explanation”=>{“relevant_text”=>[{“text”=>”dinner”}]}}, {“score”=>0.65732, “label”=>”/ food and drink/desserts and baking” @rabbigreenberg
Natural Language Processing • Formal Grammar • Inflectional Endings • Part-of-speech (POS) tagging • Parsing sentences • Sentence boundaries • Root form of words • Segment continuous text into separate words (prevalent in many languages) • Relationships of named entities to each other (who to whom, what to what, etc.) • Topic segmentation • Word meaning probability @rabbigreenberg
What’s my polarity? “I love my mobile “I’d really truly but would not “I dislike love going out in recommend it to any broken cars.” this weather!” of my colleagues.” *examples from Wikipedia @rabbigreenberg
What can I make with it? @rabbigreenberg
@rabbigreenberg
Sometimes you just need to get to the… @rabbigreenberg
@rabbigreenberg
…and just tell me What’s the mood of the news? @rabbigreenberg
WHAT ARE WE BUILDING (1) “topic” (2) (3) @rabbigreenberg
Let’s build it! @rabbigreenberg
What APIs will will be using? IBM WATSON Natural Language Analyzer API Generous free access tier Ruby SDK Documentation www.ibm.com/watson/developer NEWS API “Search worldwide news with code” Generous free access tier Ruby SDK Documentation www.newsapi.org NEXMO Messages API Generous free access tier Ruby SDK Documentation developer.nexmo.com @rabbigreenberg
Gemfile
@rabbigreenberg
Routes
@rabbigreenberg
Environment Variables
@rabbigreenberg
Controller
Defining Methods @rabbigreenberg
#inbound @rabbigreenberg
#analyze_headlines @rabbigreenberg
#get_news_headlines @rabbigreenberg
#send_whatsapp_msg @rabbigreenberg
#send_whatsapp_msg @rabbigreenberg
#send_whatsapp_msg @rabbigreenberg
#generate_jwt_token @rabbigreenberg
Giving It A Go!
@rabbigreenberg
Thank you! @rabbigreenberg https://github.com/Nexmo/mood-of-the-news
The societies we live in, the companies we work for, the media we consume and much more are all shaped by words. Words can infuriate, enlighten, bring joy or cause great despair. Natural Language Understanding gives us a window into analyzing the words that surround us for sentiment and tone.
How does Natural Language Understanding work? What insights can we glean from the data it provides?
We will take a dive into understanding how this technology works, and apply it in a Ruby app that connects Natural Language Understanding analysis, the daily headlines and social media all in one. Get ready to learn some Ruby, some human language insights and how they all intertwine!
for free. You
can too.