Presentation is loading. Please wait.

Presentation is loading. Please wait.

Music Recommendation By Daniel McEnnis. Outline Sociology of Music Recommendation Infrastructure –Relational Analysis Toolkit Description Evaluation –GATE.

Similar presentations


Presentation on theme: "Music Recommendation By Daniel McEnnis. Outline Sociology of Music Recommendation Infrastructure –Relational Analysis Toolkit Description Evaluation –GATE."— Presentation transcript:

1 Music Recommendation By Daniel McEnnis

2 Outline Sociology of Music Recommendation Infrastructure –Relational Analysis Toolkit Description Evaluation –GATE and Review Mining

3 Why do we like what we like? Personal Identity and Music –Music and Lifestyle Correlations Social Associations Peer Groups Content of the Music and Lyrics –Culture specific understanding of music –Social meanings of musical forms –Ability to understand the lyrics

4 Social Networks and Music Recommendation What is social information? –Age and personal collections/preferences –Friends’ musical tastes –Opinions of local associations or groups –Local (geographical) opinions about music –Cultural background of the person

5 Where is the Data? Play-lists, personal music collections, and recorded listening habits Social network sites such as Facebook and Live Journal Web sites such as blogs and lists of favorite web pages Relationships between these artifacts

6 What Infrastructure is Needed Toolkit for synthesizing social data. Text mining tools for analyzing web-pages, music reviews, and blogs. Play-list analyzers Content-based music analysis toolkits

7 Social Toolkit Requirements Intuitive Java-Based Graph Toolkit Arbitrary multi-valued properties on nodes Social network analysis algorithms Efficient back-end processing Scripting support for experiments

8 Relational Analysis Toolkit (RAT) Low Level –Graph –Actor (Node) –Link (Arc, Edge) High Level –Collection of algorithms –Scripting support

9 Exponential Similarity -1.3 k +2 k 0

10 Music Recommendation

11 Degree Centrality

12 Djikstra Shortest paths Djikstra’s shortest path algorithm over this graph. Closeness measures are stored in a Path object cached at the graph object. Optimized version used inside Closeness and Betweeness for performance reasons.

13 Closeness Centrality

14 Betweeness Prestige

15 Page Rank

16 Kleinberg’s HITS Generates a set of ‘hubs’ (central actors) and ‘authorities’ (prestigious actors). Intuitively good hubs (User) point (Knows) to good authorities (User) and vice versa. Implemented in naïve and optimized versions.

17 Clique Definition

18 Evaluation How well can this method recreate a persons list of liked music 4% average precision 16% average recall Standard deviation > 100 for both –Sometimes it works really well, but often doesn’t

19 Weka in RAT Artist-UserUser Music Beatles BeachBoys Monkeys Metallica ListensTo Beatles-AB + T T F F T C - F T T F T E 0 F F F F T Beach Boys-AB + T T F F F C - F T T F F E 0 F F F F F Monkeys-AB + T T F F F C - F T T F F E 0 F F F F F Metallica-AB + T T F F F C - F T T F F E 0 F F F F F

20 Weka Evaluation Same data as Ad Hoc algorithm J48 Classifier 1% Precision 62% Recall More coming….

21 Music Reviews - epinions.com Uses GATE Parts of speech analyzer Predicting positive/negative reviews Useful for tag extraction Negation problems

22 Conclusions Social information is important for music recommendation RAT has centrality algorithms, but requires more clustering and learning algorithms Music review mining ready for integration into the RAT environment

23 Future Work Evaluate with more Weka algorithms Implement graph-based clustering algorithms Implement other distance measures Implement blog and web-page text mining Integrate existing content based methods Evaluate results with a user study

24 Questions?


Download ppt "Music Recommendation By Daniel McEnnis. Outline Sociology of Music Recommendation Infrastructure –Relational Analysis Toolkit Description Evaluation –GATE."

Similar presentations


Ads by Google