A New Algorithm for Inferring User Search Goals with Feedback Sessions

Bhavesh Pandya et al. Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 5, Issue 8, (Part - 2) August 2015, pp.30-33
www.ijera.com 30 | P a g e
A New Algorithm for Inferring User Search Goals with Feedback
Sessions
Bhavesh Pandya*, Charmi Chaniyara**, Darshan Sanghavi***, Krutarth
Majithia****
*(Assistant professor, Department of Information Technology, St, Francis Institute of Technology, Mumbai
University, Maharashtra, India)
** (Assistant professor, Mumbai University, Maharashtra, India)
***(Student, Department of Information Technology, St, Francis Institute of Technology, Mumbai University,
Maharashtra, India)
****(Student, Department of Information Technology, St, Francis Institute of Technology, Mumbai University,
Maharashtra, India)
ABSTRACT
When different users may have different search goals when they submit it to a search engine. The inference and
analysis of user search goals can be very useful in improving search engine relevance and user experience. The
Novel approach to infer user search goals by analyzing search engine query logs. Once the User entered the
query, the Resultant URLs will be filtered and the Pseudo-Documents are generated. Once the Pseudo
documents are generated the Server will apply the Clustering Mechanism to URL’s. So that the URLs are listed
as different categories. Feedback sessions are constructed from user click-through logs and can efficiently reflect
the information needs of user. Second, we propose a novel approach to generate pseudo documents to better
represents the feedback sessions for clustering. Finally we proposed new criterion “Classified Average Precision
(CAP)” to evaluate the performance of inferring user search goals. Experimental results are presented using user
click-through logs from a commercial search engine to validate the effectiveness of our proposed methods.
Third, the distributions of user search goals can also be useful in applications such as re ranking web search
results that contain different user search goals.
Keywords- Classified Average Precision, Data Contents, Presentation Styles, Average Precision, Integrated
Interface Schema, Uniform Resource Locator, Mining Spanning Tree.
I. INTRODUCTION
 For a broad-topic and ambiguous query, different
users may have different search goals when they
submit it to a search engine. The inference and
analysis of user search goals can be very useful
in improving search engine relevance and user
experience. In this paper, we propose a novel
approach to infer user search goals by analyzing
search engine query logs. First, we propose a
framework to discover different user search
goals for a query by clustering the proposed
feedback sessions. Feedback sessions are
constructed from user click-through logs and can
efficiently reflect the information needs of users.
Second, we propose a novel approach to generate
pseudo-documents to better represent the
feedback sessions for clustering. Finally, we
propose a new criterion “Classified Average
Precision (CAP)” to evaluate the performance of
inferring user search goals. Experimental results
are presented using user click-through logs from
a commercial search engine to validate the
effectiveness of our proposed methods.
 Our framework consists of two parts divided by
the dashed line. In the upper part, all the
feedback sessions of a query are first extracted
from user click-through logs and mapped to
pseudo-documents. Then, user search goals are
inferred by clustering these pseudo-documents
and depicted with some keywords. Since we do
not know the exact number of user search goals
in advance, several different values are tried and
the optimal value will be determined by the
feedback from the bottom part. In the bottom
part, the original search results are restructured
based on the user search goals inferred from the
upper part. Then, we evaluate the performance of
restructuring search results by our proposed
evaluation criterion CAP. And the evaluation
result will be used as the feedback to select the
optimal number of user search goals in the upper
part..
[1] This paper highlights ” A New Algorithm
for Inferring User Search Goals with Feedback
Sessions “.For a broad-topic and ambiguous query,
different users may have different search goals when
they submit it to a search engine. The inference and
RESEARCH ARTICLE OPEN ACCESS

analysis of user search goals can be very useful in
improving search engine relevance and user
experience. In this paper, we propose a novel
approach to infer user search goals by analyzing
search engine query logs. First, we propose a
framework to discover different user search goals for
a query by clustering the proposed feedback sessions.
Feedback sessions are constructed from user click-
through logs and can efficiently reflect the
information needs of users. Second, we propose a
novel approach to generate pseudo-documents to
better represent the feedback sessions for clustering.
Finally, we propose a new criterion “Classified
Average Precision (CAP)” to evaluate the
performance of inferring user search goals.
Experimental results are presented using user click-
through logs from a commercial search engine to
validate the effectiveness of our proposed methods.
[2]This paper highlights Using Feedback Sessions for
Inferring User Search Goals. Identifying or inferring
user’s search goal from given query is a difficult job
as search engines allow users to specify queries
simply as a list of keywords which may refer to broad
topics, to technical terminology, or even to proper
nouns that can be used to guide the search process to
the relevant collection of documents. Information
needs of users are represented by queries submitted
to search engines and different users have different
search goals for a broad topic. Sometimes queries
may not exactly represent the user's information
needs due to the use of short queries with ambiguous
terms. Hence to get the best results it is necessary to
capture different user search goals.
[3] This paper “A New Algorithm for Inferring
User Search Goals with Feedback Sessions” .When
different users may have different search goals when
they submit it to a search engine. The inference and
analysis of user search goals can be very useful in
improving search engine relevance and user
experience. The Novel approach to infer user search
goals by analyzing search engine query logs. Once
the User entered the query, the Resultant URLs will
be filtered and the Pseudo-Documents are generated.
Once the Pseudo documents are generated the Server
will apply the Clustering Mechanism to URL’s.
Feedback sessions are constructed from user click-
through logs and can efficiently reflect the
information needs of user. Second, we propose a
novel approach to generate pseudo documents to
better represents the feedback sessions for clustering.
Finally we proposed new criterion “Classified
Average Precision (CAP)” to evaluate the
performance of inferring user search goals.
Experimental results are presented using user click-
through logs from a commercial search engine to
validate the effectiveness of our proposed methods.
Third, the distributions of user search goals can also
be useful in applications such as re ranking web
search results that contain different user search goals.
II. Other Existing System
We define user search goals as the information
on different aspects of a query that user groups want
to obtain. Information need is a user’s particular
desire to obtain information to satisfy his/her need.
User search goals can be considered as the clusters of
information needs for a query. The inference and
analysis of user search goals can have a lot of
advantages in improving search engine relevance and
user experience.
2.1 Problems on existing system:
 What users care about varies a lot for different
queries, finding suitable predefined search goal
classes is very difficult and impractical.
 Analyzing the clicked URLs directly from user
click-through logs to organize se arch results.
However, this method has limitations since the
number of different clicked URLs of a query
may be small. Since user feedback is not
considered, many noisy search results that are
not clicked by any users may be analyzed as
well. Therefore, this kind of methods cannot
infer user search goals precisely.
 Only identifies whether a pair of queries belongs
to the same goal or mission and does not care
what the goal is in detail.
III. System Architecture
The implementation stage involves careful
planning, investigation of the existing system and it’s
constraints on implementation, designing of methods
to achieve changeover and evaluation of changeover
methods.
3.1 Interaction Model:
Client-driven interventions:
Client-driven interventions are the means to
protect customers from unreliable services. For
example, services that miss deadlines or do not
respond at all for a longer time are replaced by other
more reliable services in future discovery operations.
Provider-driven interventions
Provider-driven interventions are desired and
initiated by the service owners to shield themselves
from malicious clients. For instance, requests of
clients performing a denial of service attack by
sending multiple requests in relatively short intervals
are blocked.
3.2 Modules:
 Preprocessing modules.
 Re-formatting web log file.
 Clustering of users.

 Association rule.
 Recommendation
Step 1: Preprocessing Module
In the preprocessing step, there are two major
tasks: re-format the log file and retrieve web pages to
local space. Log file re-formatting involves revising
the log file to an appropriate format for further steps.
Web page retrieving involves reading the URL
address part of the re-formatted log file, retrieving the
Web pages accordingly, and storing them to local
space.
Step 2: Re-Formatting Web Log File
Each tipple of the log file is a record for one
request from a certain user. For example, Figure 2
shows an IIS log file entry, as viewed in a text editor
and Table 1 lists and describes the fields used in this
work.
Step 3: Clustering
In clustering the data is been clustered. Where
the required data is been clustered into one cluster
and unwanted data into one cluster. In web document
clustering the web pages are preprocessed during
clustering the document have multiple topics. It
clears the html, xml tags from web pages.
Eliminating all punctuations, integrating the
Reformatted log files and web document clustering.
In user clustering it extract the use query and display
the clustering table. Then integration of user cluster
with web document clustering.
Step 4: Association Rule
Mining association rules among items in a large
database is one of the most important problems of
data mining. The task is to find interesting
association or correlation relationships among a large
set of data items. The typical rule mined from
database is formatted as follows:
X → Y [Support, Confidence]
It means the presence of item X leads to the presence
of item Y, with [Support]% occurrence of [X,Y] in the
whole database, and [Confidence]% occurrence of [Y]
in set of records where [X] occurred.
Step 5: Recommendation
K-mean Algorithm
K-means is one of the simplest unsupervised
learning algorithms that solve the well-known
clustering problem. The procedure follows a simple
and easy way to classify a given data set through a
certain number of clusters (assume k clusters) fixed a
priori. The main idea is to define k centroids, one for
each cluster. These centroids should be placed in a
cunning way because of different location causes
different result. So, the better choice is to place them
as much as possible far away from each other. The
next step is to take each point belonging to a given
data set and associate it to the nearest centroid.
Figure 1 Flowchart
IV. Conclusion
In this Project, a novel approach has been
proposed to infer user search goals for a query by
clustering its feedback sessions represented by
pseudo-documents. First, we introduce feedback
sessions to be analysed to infer user search goals
rather than search results or clicked URLs. Both the
clicked URLs and the unclicked ones before the last
click are considered as user implicit feedbacks and
taken into account to construct feedback sessions.
Therefore, feedback sessions can reflect user
information needs more efficiently. Second, we map
feedback sessions to pseudo-documents to
approximate goal texts in user minds. The pseudo-
documents can enrich the URLs with additional
textual contents including the titles and snippets.
Based on these pseudo-documents, user search goals
can then be discovered and depicted with some
keywords. Finally, a new criterion CAP is formulated
Y.Y.Y.Y, -, 03/20/07, 7:55:20, W3SVC2,
SERVER, X.X.X.X, 4502, 163, 3223, 200, 0,
GET, /Logo.gif, -,

to evaluate the performance of user earch goal
inference. Experimental results on user click-through
logs from a commercial search engine demonstrate
the effectiveness of our proposed methods. The
complexity of our approach is low and our approach
can be used in reality easily. For each query, the
running time depends on the number of feedback
sessions. Therefore, the running time is usually short.
In reality, our approach can discover user search
goals for some popular queries offline at first. Then,
when users submit one of the queries, the search
engine can return the results that are categorized into
different groups according to user search goals
online. Thus, users can find what they want
conveniently.
REFERENCES
[1] Zheng Lu, Student Member, IEEE,
Hongyuan Zha, Xiaokang Yang, Senior
Member, IEEE, Weiyao Lin, Member,
IEEE, and Zhaohui Zheng
[2] International Journal of Advanced Research
in Computer Engineering & Technology
(IJARCET)Volume 2, Issue 12, December
2013
[3] A New Algorithm for Inferring User Search
Goals with Feedback Session J. Shobana,
Asst. Professor in SRM University,
Department of Computer Applications,
Chennai

A New Algorithm for Inferring User Search Goals with Feedback Sessions

More Related Content

What's hot (19)

Viewers also liked (20)

Similar to A New Algorithm for Inferring User Search Goals with Feedback Sessions (20)

Recently uploaded (20)

A New Algorithm for Inferring User Search Goals with Feedback Sessions