This document discusses challenges in evaluating heterogeneous information access systems and proposes areas for future research. It notes that traditional IR evaluation focuses on system-oriented metrics using test collections, while heterogeneous search involves more complex user behaviors like non-linear browsing. Key challenges include accounting for diverse search tasks, coherence, diversity, personalization and different result presentation strategies. The document advocates better understanding user behavior through models and applying this understanding to improve evaluation metrics for heterogeneous search systems. It identifies areas for future work such as modeling task complexity, coherence and click patterns to develop more powerful evaluation frameworks.
[2024]Digital Global Overview Report 2024 Meltwater.pdf
Evaluating Heterogeneous Information Access (Position Paper)
1. Evalua&ng
Heterogeneous
Informa&on
Access
(Posi&on
Paper)
Ke
Zhou1,
Tetsuya
Sakai2,
Mounia
Lalmas3,
Zhicheng
Dou2
and
Joemon
M.
Jose1
1University
of
Glasgow
2MicrosoN
Research
Asia
3Yahoo!
Labs
Barcelona
SIGIR
2013
MUBE
workshop
2. IR
Evalua&on
• System-‐oriented
Evalua&on
(test
collec&on
+
metrics)
• User-‐oriented
Evalua&on
(interac&ve
user
study)
• Current
endeavor
to
incorporate
user
into
system-‐oriented
metrics
– Time-‐Biased
Gain
(Smucker,
Clarke.)
– U-‐measure
(Sakai,
Dou)
– etc.
5. Posi&on
• Compared
with
tradi&onal
homogeneous
search,
evalua&on
in
the
context
of
heterogeneous
informa&on
is
more
challenging
and
requires
taking
into
account
more
complex
user
behaviors
and
interac4ons.
16. Avenues
of
Research
• Be^er
understanding
of
users
– Click
models:
WSDM’12
(Chen
et
al.),
SIGIR’13
(Wang
et
al.)
– Ver&cal
orienta&on:
CIKM’10
(Sushmita
et
al.),
WWW’13
(Zhou
et
al.)
– Task
complexity:
SIGIR’12
(Arguello
et
al.)
– Task
coherence:
CIKM’12
(Arguello
et
al.)
– Diversity:
SIGIR’12
(Zhou
et
al.)
– Personaliza&on
– Non-‐linear
presenta&on
strategies
17. Avenues
of
Research
• Be^er
incorpora&on
of
learned
user
behavior
into
evalua&on
metrics
– follow
SIGIR’13
(Chuklin
et
al)
and
convert
obtained
aggregated
search
click
models
into
system-‐oriented
evalua&on
metrics.
– model
addi&onal
features
into
powerful
evalua&on
framework
(e.g.
TBG,
U-‐measure,
AS-‐
metric).