technology frontiers: text, sentiment, and sense
DESCRIPTION
Presentation by Seth Grimes at the Insight Innovation Exchange (IIEX) conference, June 17, 2013 in Philadelphis.TRANSCRIPT
![Page 1: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/1.jpg)
Technology Frontiers: Text, Sentiment, and Sense
Seth Grimes@sethgrimes
![Page 2: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/2.jpg)
A Sensemaking Story
New York Times,September 30, 2012
![Page 3: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/3.jpg)
New York Times,September 8, 1957
Valium: A Chain of Connections
![Page 4: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/4.jpg)
Natural Language Processing
By H.P. Luhn, inIBM Journal,April, 1958
http://altaplana.com/ibm-luhn58-LiteratureAbstracts.pdf
![Page 5: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/5.jpg)
Modelling Text
“Statistical information derived from word frequency and distribution is used by the machine to compute a relative measure of significance, first for individual words and then for sentences. Sentences scoring highest in significance are extracted and printed out to become the auto-abstract.”
-- H.P. Luhn, The Automatic Creation of Literature Abstracts, IBM Journal, 1958.
Luhn’s analysis of Messengers of the Nervous System, a Scientific American article http://wordle.net,
applied to the NY Times article
![Page 6: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/6.jpg)
New York Times,September 8, 1957
Luhn’s Example
![Page 7: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/7.jpg)
Close Reading
![Page 8: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/8.jpg)
![Page 9: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/9.jpg)
Can Software Make the Connection?
Mark Lombardi, George W. Bush, Harken Energy and Jackson Stephens, c. 1979-90, Detail
![Page 10: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/10.jpg)
Insight from Connections
… via graphs, clusters, categories, and counts.
… by mining the full set of available data.
![Page 11: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/11.jpg)
http://techpresident.com/news/21618/politico-facebook-sentiment-analysis-bogus
Online & Social Change Everything
![Page 12: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/12.jpg)
(Accessible) Data Everywhere
![Page 13: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/13.jpg)
Lexical, syntactic, and semantic analysis discern features including relationships in source materials.
Features = entities, measure-value pairs, concepts, topics, events, sentiment, and more.
Text analytics may draw on:
• Lexicons & taxonomies.• Statistics.• Patterns.• Linguistics.• Machine learning.
Text Analytics
![Page 14: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/14.jpg)
How?
![Page 15: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/15.jpg)
From POS to Relationships
Understand parts of speech (POS), e.g. – <subject> <verb> <object> –to discern facts and relationships.
Semantic networks such as WordNet are a disambiguation asset.
![Page 16: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/16.jpg)
Clustered Clarity
Carrot2.(open source)
![Page 17: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/17.jpg)
Platforms and ecosystems.
APIs and services.
Text and content analytics --Discerns and extracts features including
relationships from source materials.
Features = entities, key-value pairs, concepts, topics, events, sentiment, etc.
Provide (for) BI on content-sourced data.
Data integration, record linkage, data fusion.
The Back End
![Page 18: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/18.jpg)
Content, Composites, Connections
![Page 19: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/19.jpg)
Content, Composites, Connections, 2
![Page 20: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/20.jpg)
Social Sources
![Page 21: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/21.jpg)
Sentiment Analysis
“Sentiment analysis is the task of identifying positive and negative opinions, emotions, and evaluations.”
-- Wilson, Wiebe & Hoffman, 2005, “Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis”
“Sentiment analysis or opinion mining is the computational study of opinions, sentiments and emotions expressed in text… An opinion on a feature f is a positive or negative view, attitude, emotion or appraisal on f from an opinion holder.”
-- Bing Liu, 2010, “Sentiment Analysis and Subjectivity,” in Handbook of Natural Language Processing
![Page 22: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/22.jpg)
Detection, Classification
![Page 23: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/23.jpg)
Beyond Polarity
![Page 24: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/24.jpg)
Intent Analysis
http://www.aiaioo.com/whitepapers/intention_analysis_use_cases.pdf
http://sentibet.com/
![Page 25: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/25.jpg)
Complications
Sentiment may be of interest at multiple levels.Corpus / data space, i.e., across multiple sources.Document.Statement / sentence.Entity / topic / concept.
Human language is noisy and chaotic!Jargon, slang, irony, ambiguity, anaphora, polysemy,
synonymy, etc.Context is key. Discourse analysis comes into play.
Must distinguish the sentiment holder from the object:“Geithner said the recession may worsen.”
![Page 26: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/26.jpg)
Audio including speech.Images.Video.
http://www.geekosystem.com/facebook-face-recognition/
http://www.sciencedirect.com/science/article/pii/S0167639312000118
http://flylib.com/books/en/2.495.1.54/1/
Beyond Text
![Page 27: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/27.jpg)
Sensemaking
“It is convenient to divide the entire information access process into two main components: information retrieval through searching and browsing, and analysis and synthesis of results. This broader process is often referred to in the literature as sensemaking. Sensemaking refers to an iterative process of formulating a conceptual representation from of a large volume of information. Search plays only one part in this process.”
-- Marti Hearst, 2009 http://searchuserinterfaces.com/
![Page 28: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/28.jpg)
Apply new tech to old needs, e.g., automated coding.
Select from and use all available data.
Marry social to profiles and surveys.
Factor in behaviors.
Interpret according to context and needs.
Understand intent to create situational predictive models.
Explore; experiment.
Suggestions
![Page 29: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/29.jpg)
Racing On
![Page 30: Technology Frontiers: Text, Sentiment, and Sense](https://reader036.vdocuments.us/reader036/viewer/2022062511/54c65b4f4a795940598b458c/html5/thumbnails/30.jpg)
Technology Frontiers: Text, Sentiment, and Sense
Seth Grimes@sethgrimes