Intro to Sentiment Analysis

Preview:

DESCRIPTION

A brief introduction for business students in the Limerick Institute of Technology, Ireland.

Citation preview

Intro to Sentiment AnalysisIntro to Sentiment Analysis

“FAST, NEAT, AVERAGE, FRIENDLY, GOOD, GOOD” was the author’s first sentiment. “FAST, NEAT, AVERAGE, FRIENDLY, GOOD, GOOD” was the author’s first sentiment.

aka Opinion Miningaka Opinion Mining

Sentiment analysis is opinion mining.

Uses Natural Language Processing.

Dives deep into text analysis.

Leverages computational linguistics.

Develops meta data with business intelligence.

Sentiment analysis is opinion mining.

Uses Natural Language Processing.

Dives deep into text analysis.

Leverages computational linguistics.

Develops meta data with business intelligence.

Basic Opinion MiningBasic Opinion Mining

Construct a range of polarity for opinion markers.

Classify statements by their polarity.

Analyse several levels deep.

Websites are one level.

Authors are another level.

Web page is a third level.

A sentence is a fourth level.

Construct a range of polarity for opinion markers.

Classify statements by their polarity.

Analyse several levels deep.

Websites are one level.

Authors are another level.

Web page is a third level.

A sentence is a fourth level.

Ranges of PolarityRanges of Polarity

Classify emotional states.

“Angry” can be codified as “upset” or “cross”.

“Sad” may be “disappointed” or “confused”.

“Happy” may be “amazing” or “gorgeous”.

Classify emotional states.

“Angry” can be codified as “upset” or “cross”.

“Sad” may be “disappointed” or “confused”.

“Happy” may be “amazing” or “gorgeous”.

Scaling SystemsScaling Systems

Some words are negative and deserve to be minus 10.

Some words are neutral and should be equal to five.

Some words are positive and could range from six to 10.

Some words are negative and deserve to be minus 10.

Some words are neutral and should be equal to five.

Some words are positive and could range from six to 10.

Subjective and ObjectiveSubjective and Objective

Subjectivity and ObjectivitySubjectivity and Objectivity

Starts with classifying a given text (no more than a paragraph).

Mark the media text as objective or subjective.

The challenge lies in the subtlety of expression or the compound effect of multiple authors.

Proper analysis normally means removing objective statements from the given text.

Starts with classifying a given text (no more than a paragraph).

Mark the media text as objective or subjective.

The challenge lies in the subtlety of expression or the compound effect of multiple authors.

Proper analysis normally means removing objective statements from the given text.

Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis

Determine opinions based on features.

Mark the media text as objective or subjective.

The challenge lies in the subtlety of expression or the compound effect of multiple authors.

Proper analysis normally means removing objective statements from the given text.

Determine opinions based on features.

Mark the media text as objective or subjective.

The challenge lies in the subtlety of expression or the compound effect of multiple authors.

Proper analysis normally means removing objective statements from the given text.

Ambiguous and DisambiguationAmbiguous and Disambiguation

When Something is AmbiguousWhen Something is Ambiguous

Detect entity within text, such as person, place or company.

Get detailed view at entity level, not document-level.

“I love Ireland but I hate traveling on Irish roads.”

Detect entity within text, such as person, place or company.

Get detailed view at entity level, not document-level.

“I love Ireland but I hate traveling on Irish roads.”

DisambiguationDisambiguation

Detect entity within text, such as person, place or company.

Get detailed view at entity level, not document-level.

“I love Ireland but I hate traveling on Irish roads.”

Detect entity within text, such as person, place or company.

Get detailed view at entity level, not document-level.

“I love Ireland but I hate traveling on Irish roads.”

Entity-LevelEntity-Level

Detect entity within text, such as person, place or company.

Get detailed view at entity level, not document-level.

“I love Ireland but I hate traveling on Irish roads.”

Detect entity within text, such as person, place or company.

Get detailed view at entity level, not document-level.

“I love Ireland but I hate traveling on Irish roads.”

Keyword-Level SentimentKeyword-Level Sentiment

Gleans sentiment for every detected keyword.

Much more detailed than view at document-level.

BMW can determine positive comments about cars mention quality of handling.

Gleans sentiment for every detected keyword.

Much more detailed than view at document-level.

BMW can determine positive comments about cars mention quality of handling.

User-Specified SentimentUser-Specified Sentiment

You, the analyst, target specific words or phrases.

So you specify a restaurant’s name and return sentiment scores based on that name.

You cull various media texts for sentiment about a specific hotel.

You, the analyst, target specific words or phrases.

So you specify a restaurant’s name and return sentiment scores based on that name.

You cull various media texts for sentiment about a specific hotel.

Directional SentimentDirectional Sentiment

Identifies the commentator and emotional range.

First, discover the incident where emotion is expressed.

Second, determine the degree of positive or negative response.

Third, conclude who is mentioning both the product and how negatively.

Identifies the commentator and emotional range.

First, discover the incident where emotion is expressed.

Second, determine the degree of positive or negative response.

Third, conclude who is mentioning both the product and how negatively.

Disambiguation by LocationDisambiguation by Location

Identifies the exact point on the earth.

Use contextual cues.

Perhaps where something is posted or where commentator is based.

Identifies the exact point on the earth.

Use contextual cues.

Perhaps where something is posted or where commentator is based.

Disambiguation: Meta DataDisambiguation: Meta Data

Meta data provides data about data.

Links can remove ambiguity.

Past geographical movements clarify reach of commentators.

Simple internet searches can provide accurate profile data.

Meta data provides data about data.

Links can remove ambiguity.

Past geographical movements clarify reach of commentators.

Simple internet searches can provide accurate profile data.

Entity SubtypesEntity Subtypes

Author is a real person.

Author is a man.

Man’s name is Paul O’Connell.

This Paul O’Connell is Munster.

Author is a real person.

Author is a man.

Man’s name is Paul O’Connell.

This Paul O’Connell is Munster.

Exact QuotationsExact Quotations

What was said.

Who said what.

When it was said.

Where it was said.

This exactness provides context.

What was said.

Who said what.

When it was said.

Where it was said.

This exactness provides context.

Author ProfileAuthor Profile

Analyse the text.

Validate the context.

Extract the concept.

Extract the keywords.

Apply to author profile.

Determine what author’s write about.

Analyse the text.

Validate the context.

Extract the concept.

Extract the keywords.

Apply to author profile.

Determine what author’s write about.

ReferencesReferences

Turney and Pang applied methods for detecting polarity at the document level.

Pang and Snyder classified documents on a multi-way scale, such as “five stars”.

Katie Paine wrote “Measure What Matters”

Turney and Pang applied methods for detecting polarity at the document level.

Pang and Snyder classified documents on a multi-way scale, such as “five stars”.

Katie Paine wrote “Measure What Matters”

Useful LinksUseful Links

For Immediate Release G+ Community

Marketing Over Coffee Podcast

KD Paine’s Blog

The Alchemy Blog

For Immediate Release G+ Community

Marketing Over Coffee Podcast

KD Paine’s Blog

The Alchemy Blog

Continue the DiscussionContinue the Discussion

Use the Google Doc.

Consult Moodle.

Shout to @topgold

Use the Google Doc.

Consult Moodle.

Shout to @topgold

Recommended