Aruna Balasubramanian, Yun Zhou, W Bruce Croft,

1
Web Search From a Bus

• Aruna Balasubramanian, Yun Zhou, W Bruce Croft,
• Brian N Levine and Arun Venkataramani
• Department of Computer Science,
• University of Massachusetts, Amherst

2
Why web search from a bus?

• Open access point commonly available
• Intermittent internet connectivity from vehicles
  possible
• no subscription cost
• useful when no other connectivity is available
• Web search 2nd most common web activity (survey
  by pewinternet.org)

3
Connectivity characteristics of testbeds
Goal Build web search in the presence of
frequent disconnections and small connectivity
duration
4
Web search process
ltyour favorite search enginegt
Retrieving web.
Retrieving images
Retrieving.
5
Adapting to vehicular network
6
Why challenging?

• Interactive
• several exchanges between user and search engine
  needed
• Results imprecise
• response may not be relevant
• difficult to measure relevance

Thedu Proxy Architecture sustain
interaction IR contribution increase usefulness
of returned response
7
Thedu proxy

• Between vehicle and search engine
• When proxy receives query request from vehicle
• retrieves urls and snippets
• prefetches URL contents including images
• stores responses and maintains state
• When vehicle connects to proxy
• downloads pending responses

8
Client and proxy architecture
Server-side Proxy
Client-side Vehicle
Search engine
Queries for vehicle
New queries
Web interface
USE R
Queries
Fetch URL/images
Store query
Intermittent connectivity
Response bundles
Process response
Prioritize response
Responses
9
How to prioritize?

• Search engines use relevance scores to rank
  responses
• scores not comparable across queries
• Even if response is relevant it may not be useful
• Query chants 2007 needs only one response
• Thedu
• Normalize relevance scores Comparable across
  queries
• Classify query-type To capture user intent

http//www.netlab.hut.fi/chants-2007/
10
Query-Type classification

• Query-type classification
• Homepage query cnn, chants 2007
• Non-homepage query Harry potter review
• Thedu classifies using URL, snippet and title
  field
• E.g., chants 2007 on Google
• lturlgt http//www.netlab.hut.fi/chants-2007
  lt/urlgt
• ltsnippetgt Welcome to the home page of the ACM
  MobiCom workshop on Challenged Networks (CHANTS
  2007). lt/snippetgt
• lttitlegt chants workshop lt/titlegt

11
Relevance score normalization

• Modified language model framework
• D Document, Q Query, C Collection
• Normalized score
• Kullback-Leibler divergence (distance between Q
  and D)

Probability of word occurring in collection
Probability of word occurring in document
12
Thedu protocol

• 1. Sort responses in the order of normalized
  score
• 2. For response r for query q,
• 2a. Update
• 2b. If q is homepage query and do
  not send
• 2c. Else send response to vehicle

expected relevance of all response sent for a
query q
probability that r is relevant for q
13
Evaluation goals

• What is the delay in getting search results?
• How many results were relevant to the user?

14
Evaluation Tools

• DieselNet
• Indri search engine
• TREC (Text Retrieval Conference)
• Predefined web data collection (10G)
• Predefined set of queries (100 homepage 50
  content)
• Relevance judgments (which documents are relevant
  for query)

Thedus query-type classifier accuracy 88
15
Deployment on DieselNet
16
Thedu vs Proxy-less server

• Thedu
• March 26 to March 30
• Bundle responses
• Returns responses in prioritized order
• Maintains state

• Proxy-less server
• April 30 to May 5
• Bundle responses
• Returns responses as FIFO
• No state

17
Connectivity duration
Mean connection duration 35 sec Mean
disconnection duration 8 min
18
Thedu vs Proxy-less architecture
Thedu
Stateless proxy
19
Delay until first relevant response
20
Extending Thedu

• Can we use connectivity among buses to improve
  throughput?
• Are we limited to academic search engines?
• Convince commercial search providers to provide
  relevance scores
• Or, assign scores based on ranking
• Are users really happy with search results and
  delay?

traces.cs.umass.edu
21
Simulation Results
22
Inter-meeting times