Transcript Profiles Research Networking Software Users Group Meeting

Profiles Research Networking Software
Users Group Meeting
http://profiles.catalyst.harvard.edu
February 17, 2012
Agenda
• Welcome to new members
• Updates/news
• Profiles 1.0 Search
Profiles Users Group Members
UCSF
Fred Hutchinson CRC
Oregon Health Sci U
UC Davis (CBST)
U Southern California
UC San Diego
Charles Drew
U Hawaii
Arizona State
Montana State
U Colorado Denver
UW Madison
U Illinois
U Chicago
Baylor College Med
UT Southwestern
UT Houston
Jackson State (RTRN)
Ohio State
Cincinnati Children’s
Case Western
U Kentucky
Vanderbilt Stem Cell
Leadership in Med
U Alabama Birmingham
McGill University (Canada)
Ministério da Ciência e Tecnologia e Inovação (Brazil)
University of Cambridge (UK)
Clinical & Biomedical Computing Ltd (UK)
Symplectic Limited (UK)
Makerere University (Uganda)
Velammal Engineering College (India)
Nati Sci Lib, Chinese Acad of Sci (China)
Beijing Normal University (China)
University of the South Pacific (Fiji)
Harvard
Univ Minnesota
Dartmouth
Univ Mass
Boston Univ
Tufts Univ
Boston VA
Rensselaer
Univ Connecticut
Univ Rochester
NYU Med Ctr
MedMeme
Thomas Jefferson
UPenn
Johns Hopkins
USUHS-CNRM
NIH
George Wash U
Penn State
Childrens Nat Med Ctr
Wake Forest
HSSC
Georgia Tech
Piedmont Healthcare
Emory University
University Spotlights
Harvard University
UCSF
http://connects.catalyst.harvard.edu/profiles
http://profiles.ucsf.edu
South Carolina
UConn Health Center
University of Minnesota
http://profiles.healthsciencessc.org
http://profiles.uconn.edu
http://profiles.ahc.umn.edu
Wake Forest Medicne
Penn State
http://profiles.tsi.wakehealth.edu
http://profiles.psu.edu
Upcoming Conferences
• International Network for Social Network Analysis
(INSNA) Sunbelt Conference, Redondo Beach, CA,
March 12-18, 2012
• American Medical Informatics Association (AMIA) Joint
Summits on Translational Science, San Francisco, CA,
March 19-23, 2012
• CTSA Social Network Analysis Workshop, UC Davis,
Sacramento, CA, March 20-21, 2012.
Profiles RNS 1.0 Search
• Searches all content (people, publications,
concepts, etc.)
• Uses stemming and thesaurus for term expansion
• Uses ontology for search filters, faceting, expanding
and ranking of search results
• Search matches literals, not profiles
Example #1
(Person)
overview
My research is in social network
analysis and bibliometrics.
Search for “Bibliometrics”
(Person)
overview
My research is in social network
analysis and bibliometrics.
What is the chance the person
is an expert in “bibliometrics”?
Search Relevance Score
• Text Weight
– Probability that a literal node L is relevant to the
search phrase S
• Connection Weight
– Probability that node N is connected to node L
through property P
• Search Weight
– Probability that N is relevant to the search phrase
assuming N is connected to L through P and L is
relevant to the search phrase
• Relevance Score
– Search Weight * Connection Weight * Text Weight
Text Weight
(Person)
overview
My research is in social network
analysis and bibliometrics.
0.2
How relevant is “bibliometrics” to this literal?
Connection Weight
(Person)
overview
1.0
My research is in social network
analysis and bibliometrics.
Is this really this person’s overview?
Search Weight
(Person)
overview
0.5
My research is in social network
analysis and bibliometrics.
Is the person really an expert in the
topics mentioned in her overview?
Relevance Score
(Person)
overview
My research is in social network
analysis and bibliometrics.
0.5 * 1.0 * 0.2 = 0.1
There is a 10% chance the person is an expert in
“bibliometrics” based only on this overview
Example #2
My research is in social network
analysis and bibliometrics.
(Person)
Bibliometric Analysis
What is the chance the person
is an expert in “bibliometrics”?
Text Weight
My research is in social network
analysis and bibliometrics.
0.2
(Person)
Bibliometric Analysis
0.5
How relevant is “bibliometrics” to these literals?
Connection Weight
My research is in social network
analysis and bibliometrics.
(Person)
Bibliometric Analysis
Is this really the person’s overview, and
is this really the person’s research area?
Search Weight
My research is in social network
analysis and bibliometrics.
(Person)
Bibliometric Analysis
Is this person an expert in the topics in her overview,
and in the areas she actually publishes about?
Relevance Score
My research is in social network
analysis and bibliometrics.
(Person)
Bibliometric Analysis
This person is an expert in “bibliometrics” with
probabilities of 10% based only on the overview
and 12% only on the researchArea
Relevance Score
My research is in social network
analysis and bibliometrics.
(Person)
Bibliometric Analysis
P(Expert) = 1 - P(Not an Expert) = 1 - (1 - 0.1) * (1 - 0.12) = 0.208
There is a 20.8% chance the person is an expert
based on both the overview and the researchArea
Example #3 – Find “Weber”
“Griffin”
“Weber”
(Person)
similarTo
label
“Weber, Smith”
(Person)
linkedIR
(Authorship)
label
“Weber G. 2011. 3(1):147”
(Article)
label
(Concept)
“Sturge-Weber Syndrome”
Example #3 – Find “Weber”
“Griffin”
“Weber”
(Person)
similarTo
label
“Weber, Smith”
(Person)
linkedIR
(Authorship)
label
“Weber G. 2011. 3(1):147”
(Article)
label
(Concept)
“Sturge-Weber Syndrome”
Text Weight
“Griffin”
0
“Weber”
1.0
(Person)
similarTo
label
“Weber, Smith”
0.5
(Person)
linkedIR
(Authorship)
label
(Article)
label
(Concept)
“Weber G. 2011. 3(1):147”
0.25
“Sturge-Weber Syndrome”
0.33
Connection Weight
“Griffin”
“Weber”
(Person)
similarTo
0.3
label
1.0
“Weber, Smith”
(Person)
linkedIR
0.5
(Authorship)
(Article)
label
1.0
label
1.0
(Concept)
“Weber G. 2011. 3(1):147”
“Sturge-Weber Syndrome”
Search Weight
“Griffin”
“Weber”
(Person)
similarTo
0
label
1.0
“Weber, Smith”
(Person)
linkedIR
1.0
(Authorship)
(Article)
label
1.0
label
1.0
(Concept)
“Weber G. 2011. 3(1):147”
“Sturge-Weber Syndrome”
Relevance Score
“Griffin”
“Weber”
(Person)
similarTo
0*0.3*
label
1.0*1.0*0.5
(Person)
linkedIR
1.0*0.5*
(Authorship)
(Article)
label
“Weber, Smith”
“Weber G. 2011. 3(1):147”
1.0*1.0*0.25
label
“Sturge-Weber Syndrome”
1.0*1.0*0.33
(Concept)
Relevance Score
“Griffin”
“Weber”
1.0
(Person)
similarTo
0.5
label
“Weber, Smith”
(Person)
linkedIR
0.16
(Authorship)
0.31
label
“Weber G. 2011. 3(1):147”
(Article)
0.33
label
(Concept)
“Sturge-Weber Syndrome”
Search Phrase Parsing
• treatments for lung cancer
• Compare to thesaurus:
1
Cancer
1
Neoplasm
2
Cancer of the Lung
2
Lung Cancer
2
Lung Neoplasm
• Select best parsing
– treatments for lung cancer
– treatments for lung cancer 
Search Phrase Parsing
• treatments for lung cancer
• Remove stop words not in recognized phrases
– treatments for lung cancer
– treatments lung cancer
• Stemming for words not in recognized phrases
– treatment* lung cancer
• Expand using thesaurus
– “treatment*” AND (“cancer of the lung” OR “lung
cancer” OR “lung neoplasm”)
Search Options
• Pagination
– Offset, Limit
• Filter by class
– Example: only return people
• Filter by property
– Example: “cancer” and lastName = “Smith”
– Example: “cancer” and NOT facultyRank = “Full Prof.”
• Sort by property
– Example: sort by lastName, firstName, middleName
– Default: relevance score, label
Search Request XML
<SearchOptions>
<MatchOptions>
<SearchString>treatments for lung cancer</SearchString>
<ClassURI>http://xmlns.com/foaf/0.1/Person</ClassURI>
<SearchFiltersList>
<SearchFilter Property="http://xmlns.com/foaf/0.1/lastName">Smith</SearchFilter>
</SearchFiltersList>
</MatchOptions>
<OutputOptions>
<Offset>0</Offset>
<Limit>25</Limit>
<SortByList>
<SortBy IsDesc=“0" Property="http://xmlns.com/foaf/0.1/lastName" />
<SortBy IsDesc="0" Property="http://xmlns.com/foaf/0.1/firstName" />
</SortByList>
</OutputOptions>
</SearchOptions>