Embed Size (px)
DESCRIPTION
This presentation on Text Mining is part of the ARCOMEM training curriculum. Feel free to roam around or contact us on Twitter via @arcomem to learn more about ARCOMEM training on archiving Social Media.
Citation preview
University of Sheffield, NLP
Entity, Event and Opinion Recognition in ARCOMEM
University of Sheffield, UK
● © The University of Sheffield, 1995-2010This work is licenced under the Creative Commons Attribution-NonCommercial-ShareAlike Licence
University of Sheffield, NLP
What is Entity Recognition?
Entity Recognition is about recogising and classifying key Named Entities and terms in the text
A Named Entity is a Person, Location, Organisation, Date etc.
A term is a key concept or phrase that is representative of the text
Entities and terms may be described in different ways but refer to the same thing. We call this co-reference.
Mitt Romney, the favorite to win the Republican nomination for president in 2012
DatePerson Term
The GOP tweeted that they had knocked on 75,000 doors in Ohio the day prior.
Organisation
co-reference
Location
University of Sheffield, NLP
What is Event Recognition?
An event is an action or situation relevant to the domain expressed by some relation between entities or terms.
It is always grounded in time, e.g. the performance of a band, an election, the death of a person
Mitt Romney, the favorite to win the Republican nomination for president in 2012
Event DatePerson
Relation Relation
University of Sheffield, NLP
Why are Entities and Events Useful?
They can help answer the “Big 5” journalism questions (who, what, when, where, why)
They can be used to categorise the texts in different ways
● look at all texts about Obama.
They can be used as targets for opinion mining
● find out what people think about President Obama
When linked to an ontology and/or combined with other information they can be used for reasoning about things not explicit in the text
● seeing how opinions about different American presidents has changed over the years
University of Sheffield, NLP
Opinions
Opinion mining is about finding out what people think
A positive opinion about Romney
A negative opinion about the Republican volunteers
We analyse the texts and classify opinionated statements with: a polarity (positive or negative)a score (strength of opinion)a target (which entity or event the opinion is about)
Romney was the perfect candidate, and he was the President this country needs.
Such apathy among the Republican volunteers is disgusting.
University of Sheffield, NLP
Finding Opinions is not trivial
We can use sentiment dictionaries to look up words like “disgusting” and “perfect” and match them to a sentiment
But this isn't enough on its own.
We have to make sure to match the sentiment to the correct target (entity)
We have to deal with negative words and their scope
“Happy” and “not happy” have opposite sentiment
But “not great” does not imply negative sentiment
We have to deal with things like sarcasm, especially in tweets.
“Aahh how sweet it is to wake up to ignorance and stupidity :-)”
Why do we want to find opinions?
• Opinion mining allows us to answer questions such as:• What are the opinions on crucial social events and the key
people involved?• How are these opinions distributed in relation to demographic
user data?• How have these opinions evolved?• Who are the opinion leaders?• What is their impact and influence?
Try out some opinion mining
http://demos.gate.ac.uk/arcomem/opinions/
