Review Mining for Music Digital Libraries: Phase II J. Stephen Downie, Xiao Hu The International Music Information Retrieval Systems Evaluation Lab (IMIRSEL)

Review Mining for Music Digital Libraries: Phase II

J. Stephen Downie, Xiao HuThe International Music Information Retrieval Systems Evaluation Lab

(IMIRSEL)

University of Illinois at Urbana-Champaign

THE ANDREW W. MELLON FOUNDATION

Background & Motivation

ClassifyReviews

Identify User Descriptions

Connect toObjects

CustomerReviews

Epinions.com

Positive

Negative

Description 1Description 1Description 1Description 1

Description 1Description 1Description 1Description 1

D1 D2 D3

D1 D2 D3

Phase IIPhase I Future

Review mining: phase I

Phase IIMining frequent descriptive patterns in positive and negative reviews

Reviews Positive NegativeTotal Reviews 400 400

Total Sentences 63118 30053

Total Words 1027713 447603

Avg. (STD ) sentences per review 157.80 (75.49) 75.13 (41.62)

Avg. (STD) words per sentence 16.28 (14.43) 14.89 (12.24)

sets of words used by users to express feelings/opinions

Frequent Descriptive Pattern Mining (FDPM)Finds patterns consisting of items that frequently

occur together in individual transactions Items = candidate descriptive words (terms)

= adjectives, adverbs and verbs, no nounsTransactions = review sentences

Items

Transactions

Data/Text-to-Knowledge (D2K/T2K) Toolkits

POS tagging

Frequent pattern mining

Findings

Digging deeper and deeper to find out what makes good things good and bad things bad….

Single term patterns

Positive Reviews Negative Reviews

not – 3417 sentencesgood – 1621 sentences:

1/4 of all sentences

not – 1915 sentencesgood – 1025 sentences:

1/3 of all sentencesGood = Bad?!

good in a negative context Negation: “Nothing is good.”

“It just doesn't sound good.”Song titles:

“Good Charlotte, you make me so mad.”“Feels So Good is dated and reprehensibly bad.”

Rhetoric: “And this is a good ruiner: …” “What a waste of my good two dollars…”

Faint praise: “…the only good thing… is the

packaging.” Expressions:

“You all have heard … the good old cliché.”

Double term patterns

Positive Reviews

Negative Reviews

not good not realli

realli good not listen not great

not goodnot badnot reallinot soundrealli good

Good Bad?!

Triple term patternsPositive Reviews Negative

Reviews

sing open melodsing smooth melodsing fill melodsing smooth opennot realli goodsing lead melodsound realli goodsing plai melodaccompani sing melodsing soft melod

not realli goodnot realli listen bad not good bad not sound pretti tight spitbad not don’trealli not don’trealli bad notpretti bad notnot sing sound

Comparison to an earlier study

Cunningham et al. "The Pain, The Pain": Modeling music information behavior and the songs we hate. In Proc. of ISMIR ’05

What is the worst song ever?

Comparison to an earlier studyThis Study Cunningham et al

‘05

bad really

annoying bad

hate worst

really annoying

inane boring

horrible horrible

stupid awful

worst hate

awful stupid

crap crap

bore inane

Conclusions

Triple-term patterns necessary: Need to dig deeper to capture users’

emotional orientation/feelings toward music objects

Findings consistent with earlier workCustomer reviews are an excellent

resource for studying the underlying intentions and contributing features of user-generated metadata

Future work

Non-music cases Criticism mining on book and movie

reviews Other facets of music reviews

Recommended usage metadataOther feature studies

Stylistics in customer reviews Naïve Bayesian feature ranking Noun pattern mining in different genres

Questions?

Thank you!

THE ANDREW W. MELLON FOUNDATION

References

Han, J., Pei, J., and Yin, Y. Mining frequent patterns without candidate generation. In Proceedings of the ACM SIGMOD 2000. 1-12. 

Hu, X., Downie J.S., West K., and Ehmann A. Mining Music Reviews: Promising Preliminary Results. In Proceedings of the 6th International Symposium on Music Information Retrieval. 2005, 536-539.

Welge, M., et al. Data to Knowledge (D2K) An Automated Learning Group Report. NCSA, University of Illinois at Urbana-Champaign, 2003. (http://alg.ncsa.uiuc.edu)