Combining evidence for automatic Web session identification

He, Daqing; Göker, Ayşe; Harper, David J.

doi:10.1016/s0306-4573(01)00060-7

Cited by 161 publications

(198 citation statements)

References 10 publications

Supporting

Mentioning

192

Contrasting

Order By: Relevance

“…These results provided statistical proof that Web users demonstrate a certain way of behavior when they are about to make topic shifts or continue on a topic, which is exacerbated when a certain combination of search pattern and time interval occurs. He, et al (2002) proposed a topic identification algorithm that uses Dempster-Shafer Theory (1976) and genetic algorithms. Their algorithm automatically identifies topic changes using statistical data from Web search logs.…”

Section: Introduction and Related Researchmentioning

confidence: 99%

See 1 more Smart Citation

Investigating the performance of automatic new topic identification across multiple datasets

Özmutlu

Çavdur

Spink

et al. 2006

Proc of Assoc for Info

View full text Add to dashboard Cite

show abstract

Section: Introduction and Related Researchmentioning

confidence: 99%

“…Their algorithm automatically identifies topic changes using statistical data from Web search logs. He et al (2002) used the search pattern and duration of a query for new topic identification. Their approach was replicated on Excite search engine data (Ozmutlu and Cavdur, 2005a).…”

Section: Introduction and Related Researchmentioning

confidence: 99%

Investigating the performance of automatic new topic identification across multiple datasets

Özmutlu

Çavdur

Spink

et al. 2006

Proc of Assoc for Info

View full text Add to dashboard Cite

show abstract

“…During this paper, our main contribution is to propose a completely unique query descriptor for scrutiny queries. this is often supported a key insight -program results may themselves be wont to establish query similarity; and so incorporate each content and click on through info [11][12][13] [14]. Supported this, we tend to additionally outline a replacement similarity metric which will be utilized in any distance primarily based clump algorithmic rule.…”

Section: Related Workmentioning

confidence: 99%

Top-K Search Query Grouping using SOM Clustering for Search Engine

Uddin¹,

Nandanwar²

2015

IJCA

View full text Add to dashboard Cite

Clustering is important task for any recommendation system. Clustering method suggested by many researchers for search engine optimization. Search engine help user for better searching by user's query recommendation. Clustering is helpful for finding actual relation between different queries which are not same as they seems. But do clustering of user query is also a difficult task because of user enters lots of type and varying queries. Many time these queries may very short to get their real meaning and also can generate different meanings. Any single query may have various meaning on other hand many different query words may have common meaning for searching contents. Lots of clustering methods are given in last decades for search engine optimization but these methods unable to proper utilization various information hidden in user query log. This paper gives a novel clustering approach based on to identify query similarity and apply SOM clustering for effective clustering results. We propose a novel similarity matrix for user queries by uses of URL clicked by user trough searching results. Text similarity and time similarity are also measure for calculating similarity between two queries. This method shows good results within clustering performance to compare with other existing methods.

show abstract

“…Technically, we made use of previous studies on session identification, see, e.g., [2,5,8,2,11]. Note that the concrete definition of session and thus the methods chosen for session identification necessarily depend on the purpose of the session identification.…”

Section: Related Workmentioning

confidence: 99%

“…For studies on the influence of search patterns, in combination with the difference of time stamps, the reader is referred to [2]. The system described therein relies on a probabilistic model for session identification based on search patterns.…”

Section: Related Workmentioning

confidence: 99%

Empirical Analysis of the Rank Distribution of Relevant Documents in Web Search

Shen

Zilles

Holte

2008

2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology

View full text Add to dashboard Cite

This paper proposes an empirical approach for analyzing the rank distribution of relevant documents in web search. From a methodological point of view a new transaction log analysis method is proposed; the relevance of documents is studied over transaction sessions rather than single transactions. From a practical point of view the paper provides insights about the actual rank distribution of relevant documents in web search, with several consequences for the design of applications related to web search.

show abstract

Combining evidence for automatic Web session identification

Cited by 161 publications

References 10 publications

Investigating the performance of automatic new topic identification across multiple datasets

Investigating the performance of automatic new topic identification across multiple datasets

Top-K Search Query Grouping using SOM Clustering for Search Engine

Empirical Analysis of the Rank Distribution of Relevant Documents in Web Search

Contact Info

Product

Resources

About