![Page 1: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/1.jpg)
807 - TEXT ANALYTICS
Massimo Poesio
Lecture 4: Sentiment analysis (aka Opinion Mining)
![Page 2: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/2.jpg)
FACTS AND OPINIONS
• Two main types of textual information on the Web: FACTS and OPINIONS
• Current search engines search for facts (assume they are true)– Facts can be expressed with topic keywords.
![Page 3: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/3.jpg)
THERE IS PLENTY OF OPINIONS IN THE WEB
![Page 4: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/4.jpg)
SENTIMENT ANALYSIS
• (also known as opinion mining)• Attempts to identify the opinion/sentiment
that a person may hold towards an object
Sentiment Analysis
Positive
Negative
Neutral
![Page 5: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/5.jpg)
Components of an opinion
• Basic components of an opinion:– Opinion holder: The person or organization that
holds a specific opinion on a particular object.– Object: on which an opinion is expressed– Opinion: a view, attitude, or appraisal on an object
from an opinion holder.
![Page 6: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/6.jpg)
SENTIMENT ANALYSIS GRANULARITY
• At the document (or review) level:– Task: sentiment classification of reviews– Classes: positive, negative, and neutral– Assumption: each document (or review) focuses on a single
object (not true in many discussion posts) and contains opinion from a single opinion holder.
![Page 7: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/7.jpg)
DOCUMENT-LEVEL SENTIMENT ANALYSIS EXAMPLE
![Page 8: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/8.jpg)
SENTIMENT ANALYSIS GRANULARITY
• At the document (or review) level:– Task: sentiment classification of reviews– Classes: positive, negative, and neutral– Assumption: each document (or review) focuses on a single
object (not true in many discussion posts) and contains opinion from a single opinion holder.
• At the sentence level:– Task 1: identifying subjective/opinionated sentences
• Classes: objective and subjective (opinionated)– Task 2: sentiment classification of sentences
• Classes: positive, negative and neutral.• Assumption: a sentence contains only one opinion; not true in many
cases.• Then we can also consider clauses or phrases.
![Page 9: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/9.jpg)
SENTENCE-LEVEL SENTIMENT ANALYSIS EXAMPLE
Id: Abc123 on 5-1-2008 “I bought an iPhone a few days ago. It is such a nice phone. The touch screen is really cool. The voice quality is clear too.
It is much better than my old Blackberry, which was a terrible phone and so difficult to type with its tiny keys. However, my mother was mad with me as I did not tell her before I bought the phone. She also thought the phone was too expensive, …”
![Page 10: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/10.jpg)
SENTENCE-LEVEL SENTIMENT ANALYSIS
Id: Abc123 on 5-1-2008 “I bought an iPhone a few days ago. It is such a nice phone. The touch screen is really cool. The voice quality is clear too.
It is much better than my old Blackberry, which was a terrible phone and so difficult to type with its tiny keys. However, my mother was mad with me as I did not tell her before I bought the phone. She also thought the phone was too expensive, …”
![Page 11: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/11.jpg)
SENTENCE-LEVEL SENTIMENT ANALYSIS
Id: Abc123 on 5-1-2008 “I bought an iPhone a few days ago. It is such a nice phone. The touch screen is really cool. The voice quality is clear too.
It is much better than my old Blackberry, which was a terrible phone and so difficult to type with its tiny keys. However, my mother was mad with me as I did not tell her before I bought the phone. She also thought the phone was too expensive, …”
![Page 12: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/12.jpg)
SENTIMENT ANALYSIS GRANULARITY
• At the feature level:– Task 1: Identify and extract object features that
have been commented on by an opinion holder (e.g., a reviewer).
– Task 2: Determine whether the opinions on the features are positive, negative or neutral.
– Task 3: Group feature synonyms.• Produce a feature-based opinion summary of multiple
reviews.
![Page 13: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/13.jpg)
SENTIMENT ANALYSIS GRANULARITY
• At the feature level:– Task 1: Identify and extract object features that have been
commented on by an opinion holder (e.g., a reviewer).– Task 2: Determine whether the opinions on the features
are positive, negative or neutral.– Task 3: Group feature synonyms.
• Produce a feature-based opinion summary of multiple reviews.
• Opinion holders: identify holders is also useful, e.g., in news articles, etc, but they are usually known in the user generated content, i.e., authors of the posts.
![Page 14: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/14.jpg)
FEATURE-LEVEL SENTIMENT ANALYSIS
![Page 15: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/15.jpg)
ENTITY AND ASPECT (Hu and Liu, 2004; Liu, 2006)
![Page 16: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/16.jpg)
OPINION TARGET
![Page 17: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/17.jpg)
A DEFINITION OF OPINION (Liu, Ch. in NLP handbook, 2010)
![Page 18: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/18.jpg)
SENTIMENT ANALYSIS: THE TASK
![Page 19: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/19.jpg)
Applications• Businesses and organizations:
– product and service benchmarking.– market intelligence.– Business spends a huge amount of money to find consumer
sentiments and opinions.• Consultants, surveys and focused groups, etc
• Individuals: interested in other’s opinions when – purchasing a product or using a service, – finding opinions on political topics
• Ads placements: Placing ads in the user-generated content– Place an ad when one praises a product.– Place an ad from a competitor if one criticizes a product.
• Opinion retrieval/search: providing general search for opinions.
![Page 20: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/20.jpg)
DOCUMENT-LEVEL SENTIMENT ANALYSIS
![Page 21: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/21.jpg)
DOCUMENT-LEVEL SENTIMENT ANALYSIS
![Page 22: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/22.jpg)
DOCUMENT-LEVEL SENTIMENT ANALYSIS = TEXT CLASSIFICATION
![Page 23: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/23.jpg)
ASSUMPTIONS AND GOALS
![Page 24: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/24.jpg)
LEXICON-BASED APPROACHES
• Use sentiment and subjectivity lexicons• Rule-based classifier– A sentence is subjective if it has at least two words
in the lexicon– A sentence is objective otherwise
![Page 25: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/25.jpg)
SUPERVISED CLASSIFICATION
• Treat sentiment analysis as a type of classification• Use corpora annotated for subjectivity and/or
sentiment• Train machine learning algorithms:– Naïve bayes– Decision trees– SVM – …
• Learn to automatically annotate new text
![Page 26: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/26.jpg)
TYPICAL SUPERVISED APPROACH
![Page 27: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/27.jpg)
FEATURES FOR SUPERVISED DOCUMENT-LEVEL SENTIMENT ANALYSIS
• A large set of features have been tried by researchers (see e.g., work here at Essex by Roseline Antai)– Terms frequency and different IR weighting
schemes as in other work on classification– Part of speech (POS) tags– Opinion words and phrases– Negations– Syntactic dependency
![Page 28: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/28.jpg)
EASIER AND HARDER PROBLEMS
• Tweets from Twitter are probably the easiest– short and thus usually straight to the point
• Reviews are next – entities are given (almost) and there is little noise
• Discussions, comments, and blogs are hard. – Multiple entities, comparisons, noisy, sarcasm, etc
![Page 29: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/29.jpg)
ASPECT-BASED SENTIMENT ANALYSIS
• Sentiment classification at the document or sentence (or clause) levels are useful, but do not find what people liked and disliked.
• They do not identify the targets of opinions, i.e., ENTITIES and their ASPECTS
• Without knowing targets, opinions are of limited use.
![Page 30: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/30.jpg)
ASPECT-BASED SENTIMENT ANALYSIS
• Much of the research is based on online reviews• For reviews, aspect-based sentiment analysisis
easier because the entity (i.e., product name) is usually known– Reviewers simply express positive and negative opinions
on different aspects of the entity.• For blogs, forum discussions, etc., it is harder: – both entity and aspects of entity are unknown– there may also be many comparisons– and there is also a lot of irrelevant information.
![Page 31: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/31.jpg)
BRIEF DIGRESSION
• Regular opinions: Sentiment/opinion expressions on some target entities– Direct opinions: The touch screen is really cool– Indirect opinions: “After taking the drug, my pain
has gone”• COMPARATIVE opinions: Comparisons of
more than one entity.– “iPhone is better than Blackberry”
![Page 32: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/32.jpg)
Find entities (entity set expansion)
• Although similar, it is somewhat different from the traditional named entity recognition (NER). (See next lectures)
• E.g., one wants to study opinions on phones– given Motorola and Nokia, find all phone brands
and models in a corpus, e.g., Samsung, Moto,
![Page 33: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/33.jpg)
Feature/Aspect extraction
• May extract frequent nouns and noun phrases– Sometimes limited to a set known to be related to
the entity of interest or using part discriminators– e.g., for a scanner entity “scanner”, “scanner has”
• opinion and target relations – Proximity or syntactic dependency
• Standard IE methods– Rule-based or supervised learning – Often HMMs or CRFs (like standard IE)
![Page 34: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/34.jpg)
Aspect extraction using dependency grammar
![Page 35: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/35.jpg)
RESOURCES FOR SENTIMENT ANALYSIS
• Lexicons• General Inquirer (Stone et al., 1966)• OpinionFinder lexicon (Wiebe & Riloff,
2005)• SentiWordNet (Esuli & Sebastiani, 2006)
• Annotated corpora• Used in statistical approaches (Hu
& Liu 2004, Pang & Lee 2004)• MPQA corpus (Wiebe et. al, 2005)
• Tools • Algorithm based on minimum
cuts (Pang & Lee, 2004) • OpinionFinder (Wiebe et. al, 2005)
![Page 36: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/36.jpg)
Lexical resources for Sentiment and Subjectivity Analysis
Overview
![Page 37: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/37.jpg)
Sentiment (or opinion) lexica
![Page 38: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/38.jpg)
Sentiment lexica
![Page 39: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/39.jpg)
40
Sentiment-bearing words
ICWSM 2008
• Adjectives Hatzivassiloglou & McKeown 1997, Wiebe 2000, Kamps & Marx 2002, Andreevskaia & Bergler 2006
– positive: honest important mature large patient
• Ron Paul is the only honest man in Washington. • Kitchell’s writing is unbelievably mature and is only
likely to get better. • To humour me my patient father agrees yet again to my
choice of film
![Page 40: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/40.jpg)
41
Negative adjectives
ICWSM 2008
• Adjectives– negative: harmful hypocritical inefficient insecure• It was a macabre and hypocritical circus. • Why are they being so inefficient ? bjective: curious,
peculiar, odd, likely, probably
![Page 41: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/41.jpg)
42
Subjective adjectives
ICWSM 2008
• Adjectives – Subjective (but not positive or negative
sentiment): curious, peculiar, odd, likely, probable• He spoke of Sue as his probable successor.• The two species are likely to flower at different times.
![Page 42: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/42.jpg)
43
Other words
ICWSM 2008
• Other parts of speech Turney & Littman 2003, Riloff, Wiebe & Wilson 2003, Esuli & Sebastiani 2006
– Verbs• positive: praise, love• negative: blame, criticize• subjective: predict
– Nouns• positive: pleasure, enjoyment• negative: pain, criticism• subjective: prediction, feeling
![Page 43: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/43.jpg)
44
Phrases
ICWSM 2008
• Phrases containing adjectives and adverbs Turney 2002, Takamura, Inui & Okumura 2007
– positive: high intelligence, low cost– negative: little variation, many troubles
![Page 44: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/44.jpg)
45
Sentiment lexica
ICWSM 2008
• Human-created– WordNet Affect
• Semi-automatic– SentiWordNet 3.0
• Fully automatic– SenticNet 2.0
![Page 45: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/45.jpg)
46
(Semi) Automatic creation of sentiment lexica
ICWSM 2008
• Find relevant words, phrases, patterns that can be used to express subjectivity
• Determine the polarity of subjective expressions
![Page 46: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/46.jpg)
FINDING POLARITY IN CORPORA USING PATTERNS
![Page 47: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/47.jpg)
48
USING PATTERNS
ICWSM 2008
• Lexico-syntactic patterns Riloff & Wiebe 2003
• way with <np>: … to ever let China use force to have its way with …
• expense of <np>: at the expense of the world’s security and stability
• underlined <dobj>: Jiang’s subdued tone … underlined his desire to avoid disputes …
![Page 48: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/48.jpg)
DICTIONARY-BASED METHODS
![Page 49: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/49.jpg)
SEMI-SUPERVISED LEARNING(Esuti and Sebastiani, 2005)
![Page 50: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/50.jpg)
Corpora for Sentiment and Subjectivity Analysis
Overview
![Page 51: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/51.jpg)
52
MPQA
ICWSM 2008
• MPQA: www.cs.pitt.edu/mqpa/databaserelease (version 2)
• English language versions of articles from the world press (187 news sources)
• Also includes contextual polarity annotations (later)
• Themes of the instructions:– No rules about how particular words should be annotated.
– Don’t take expressions out of context and think about what they could mean, but judge them as they are used in that sentence.
![Page 52: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/52.jpg)
53
Definitions and Annotation Scheme
ICWSM 2008
• Manual annotation: human markup of corpora (bodies of text)
• Why? – Understand the problem– Create gold standards (and training data)
Wiebe, Wilson, Cardie LRE 2005Wilson & Wiebe ACL-2005 workshopSomasundaran, Wiebe, Hoffmann, Litman ACL-2006 workshopSomasundaran, Ruppenhofer, Wiebe SIGdial 2007Wilson 2008 PhD dissertation
![Page 53: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/53.jpg)
54
Overview
ICWSM 2008
• Fine-grained: expression-level rather than sentence or document level
• Annotate – Subjective expressions– material attributed to a source, but presented
objectively
![Page 54: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/54.jpg)
OTHER CORPORA
• The Movie Review data created by Pang and Lee– http://www.cs.cornell.edu/People/pabo/movie-review-data/
• The Semeval 2007 and 2014 (sentiment analysis in Twitter) shared tasks data– http://alt.qcri.org/semeval2014/task9/
• The Kaggle 2014 competition for Sentiment Analysis on movie reviews– https://www.kaggle.com/c/sentiment-analysis-on-movie-reviews
![Page 55: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/55.jpg)
TOOLS
![Page 56: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/56.jpg)
OPINE
![Page 57: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/57.jpg)
OPINION SUMMARIES
![Page 58: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/58.jpg)
GOOGLE PRODUCTS
![Page 59: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/59.jpg)
READINGS
• Bo Pang & Lillian Lee, 2008 – Opinion Mining and Sentiment Analysis – Foundations and Trends in Information Retrieval, v. 2, 1-2– On the website
![Page 60: 807 - TEXT ANALYTICS Massimo Poesio Lecture 4: Sentiment analysis (aka Opinion Mining)](https://reader036.vdocuments.us/reader036/viewer/2022062714/56649cff5503460f949d01e3/html5/thumbnails/60.jpg)
ACKNOWLEDGMENTS
• Some slides borrowed from– Janyce Wiebe’s tutorials– Bing Liu’s tutorials– Ronen Feldman’s IJCAI 2013 tutorial