Title: Web Search Personalization via Social Bookmarking and Tagging Michael G. Noll
1Web Search Personalization via Social
Bookmarking andTagging Michael G. Noll
Christoph MeinelHasso-Plattner-Institut an der
Universitat Potsdam, GermanyISWC 2007
- Advisor Prof. Hsin-Hsi Chen
- Reporter Yu-Hui Chang
- 2008/07/30
2Introduction
3Social bookmarking and tagging
- social bookmarking
- publicly sharing your bookmarks with others
- including any additional metadata
- tagging / folksonomies
- Users annotate Documents with with a flat,
unstructured list of keywords called Tags
4Web search personalization
- integration of user-specific data to improve
results / advertising - two main approaches
- modify user's query
- nyt gt new york times
- 2. re-rank search results based on user profile
5Personalization Technique
6Personalization
- Input
- user profile document profiles
- Via social bookmarking and tagging
- Algorithm
- calculate Similarity(user, document) for all docs
- sort documents by similarity from highest to
lowest - Output
- re-ranked search result list
7Profile
- user profile
- Tagmarking
- A user search research internet security
- gthe/she can click single button
- to bookmark a document with auto translate tag
research, internet, security - document profiles
- Communicating with the bookmarking service over
its web API
Tagmarking
8Personalization
- Complete process of web search personalization
- every step done in real-time
9Data Aggregation User Profile
n documents
m tags
10Data Aggregation Doc. Profile
- Documents profile example
n users
Mu
m tags
11Similarity
- Similarity(u ,d)puT?pd
- pd simply normalization of document profile,
reset matrix element with only 1 and 0 two values
( True or False)
12Similarity example
13 19 2 10 21 34
1 1 1 1 1 1
1301912010121034163
13Similarity score properties
- the key factor unmodified user profile
- Promotes known and similar doc., demotes those
unknown or non-similar doc. - more sophisticated normalization for both user
and document is on-going - Score of unknown document gt 0!!!
- most critical factor in practice
- do we have sufficient data to make all this
work?
14Personalization
- system setup
- server social bookmarking service
- client browser add-on
- modification of search engine UI by updating the
DOM tree of the search result pages in real-time
15(No Transcript)
16Re-rank example
- a user with a strong interest in information
technology and network security
17(No Transcript)
18Experiment and Evaluation
19Experiment
- Del.icio.us
- Public social bookmarking service
- Large user community
- Key question
- Quantitative analysis
- How many social annotations in practice?
- Qualitative analysis
- Quality evaluation
20Quantitative analysis
- test set
- 140 popular tags on del.icio.us
- 1400 search results link (top 10 results )
- totaling
- 981,989 bookmarks
- 20,498 tag annotations (2,300 unique)
21Quantitative analysis
22Quantitative analysis
Percentage of links with at least 1 tag
- we can expect to personalize approx. 85 (in the
1st page) per query in practice
23Qualitative analysis
- For each query, participants were presented two
search result lists - original list from Google Search
- The personalized version
- 8 participants evaluate the top 10 results for
13 queries each - Participants job researchers, web masters,
software developers, system administrators - The average number of bookmarks for a participant
was 153.
24Qualitative analysis
Worse
Personalized version Better
Equal
- Some discussions
- Expert user profiles
- Disambiguate words and contexts
25Conclusion
26Conclusion
- proposed personalization approach is feasible and
viable in practice - already sufficient user-supplied metadata
available - initial evaluation of personalization quality
shows very promising results - Open Access
- http//www.michael-noll.com/dmoz100k06/ - data
set - http//www.michael-noll.com/delicious-api/ -
scripts
27