Performance evaluation of web search engines in image retrieval: An experimental study

2021 ◽  
pp. 026666692110102
Author(s):  
Mehrdad (Mozaffar) CheshmehSohrabi ◽  
Elham Adnani Sadati
Keyword(s):  
Experimental Study ◽  
Performance Evaluation ◽  
Image Retrieval ◽  
Search Engine ◽  
Search Engines ◽  
Web Search ◽  
Image Search ◽  
Intense Competition ◽  
Significant Difference ◽  
General Search

This experimental study used a checklist to evaluate the performance of seven search engines consisting of four Image General Search Engines (IGSEs) (namely, Google, Yahoo DuckDuckGo and Bing), and three Image Specialized Search Engines (ISSEs) (namely, Flicker, PicSearch, and GettyImages) in image retrieval. The findings indicated that the recall average of Image General Search Engines and Image Specialized Search Engines was found to be 76.32% and 24/51% with the precision average of 82/08% and 32/21%, respectively. As the results showed, Yahoo, Google and DuckDuckGo ranked at the top in image retrieval with no significant difference. However, a remarkable superiority with almost 50% difference was observed between the general and specialized image search engines. It was also found that an intense competition existed between Google, Yahoo and DuckDuckGo in image retrieval. The overall results can provide valuable insights for new search engine designers and users in choosing the appropriate search engines for image retrieval. Moreover, the results obtained through the applied equations could be used in assessing and evaluating other search tools, including search engines.

Retrieval effectiveness of image search engines

2019 ◽  
Vol 37 (1) ◽  
pp. 173-184 ◽  
Author(s):  
Aabid Hussain ◽  
Sumeer Gul ◽  
Tariq Ahmad Shah ◽  
Sheikh Shueb
Keyword(s):  
Image Retrieval ◽  
Search Engine ◽  
Search Engines ◽  
Keyword Search ◽  
Image Search ◽  
Image Size ◽  
Test Bed ◽  
Content Type ◽  
Retrieval Effectiveness ◽  
Search Feature

Purpose The purpose of this study is to explore the retrieval effectiveness of three image search engines (ISE) – Google Images, Yahoo Image Search and Picsearch in terms of their image retrieval capability. It is an effort to carry out a Cranfield experiment to know how efficient the commercial giants in the image search are and how efficient an image specific search engine is. Design/methodology/approach The keyword search feature of three ISEs – Google images, Yahoo Image Search and Picsearch – was exploited to make search with keyword captions of photos as query terms. Selected top ten images were used to act as a testbed for the study, as images were searched in accordance with features of the test bed. Features to be looked for included size (1200 × 800), format of images (JPEG/JPG) and the rank of the original image retrieved by ISEs under study. To gauge the overall retrieval effectiveness in terms of set standards, only first 50 result hits were checked. Retrieval efficiency of select ISEs were examined with respect to their precision and relative recall. Findings Yahoo Image Search outscores Google Images and Picsearch both in terms of precision and relative recall. Regarding other criteria – image size, image format and image rank in search results, Google Images is ahead of others. Research limitations/implications The study only takes into consideration basic image search feature, i.e. text-based search. Practical implications The study implies that image search engines should focus on relevant descriptions. The study evaluated text-based image retrieval facilities and thereby offers a choice to users to select best among the available ISEs for their use. Originality/value The study provides an insight into the effectiveness of the three ISEs. The study is one of the few studies to gauge retrieval effectiveness of ISEs. Study also produced key findings that are important for all ISE users and researchers and the Web image search industry. Findings of the study will also prove useful for search engine companies to improve their services.

scholarly journals Study of Search Engine Transaction Logs Shows Little Change in How Users use Search Engines

2006 ◽  
Vol 1 (3) ◽  
pp. 67
Author(s):  
David Hook
Keyword(s):  
Search Engine ◽  
Search Engines ◽  
World Wide ◽  
Web Search ◽  
Result Page ◽  
Significant Difference ◽  
The Us ◽  
The World ◽  
The U.S ◽  
Over Time

A review of: Jansen, Bernard J., and Amanda Spink. “How Are We Searching the World Wide Web? A Comparison of Nine Search Engine Transaction Logs.” Information Processing & Management 42.1 (2006): 248-263. Objective – To examine the interactions between users and search engines, and how they have changed over time. Design – Comparative analysis of search engine transaction logs. Setting – Nine major analyses of search engine transaction logs. Subjects – Nine web search engine studies (4 European, 5 American) over a seven-year period, covering the search engines Excite, Fireball, AltaVista, BWIE and AllTheWeb. Methods – The results from individual studies are compared by year of study for percentages of single query sessions, one-term queries, operator (and, or, not, etc.) usage and single result page viewing. As well, the authors group the search queries into eleven different topical categories and compare how the breakdown has changed over time. Main Results – Based on the percentage of single query sessions, it does not appear that the complexity of interactions has changed significantly for either the U.S.-based or the European-based search engines. As well, there was little change observed in the percentage of one-term queries over the years of study for either the U.S.-based or the European-based search engines. Few users (generally less than 20%) use Boolean or other operators in their queries, and these percentages have remained relatively stable. One area of noticeable change is in the percentage of users viewing only one results page, which has increased over the years of study. Based on the studies of the U.S.-based search engines, the topical categories of ‘People, Place or Things’ and ‘Commerce, Travel, Employment or Economy’ are becoming more popular, while the categories of ‘Sex and Pornography’ and ‘Entertainment or Recreation’ are declining. Conclusions – The percentage of users viewing only one results page increased during the years of the study, while the percentages of single query sessions, one-term sessions and operator usage remained stable. The increase in single result page viewing implies that users are tending to view fewer results per web query. There was also a significant difference in the percentage of queries using Boolean operators between the US-based and the European-based search engines. One of the study’s findings was that results from a study of a particular search engine cannot necessarily be applied to all search engines. Finally, web search topics show a trend towards information or commerce searching rather than entertainment.

scholarly journals The Matter of Chance: Auditing Web Search Results Related to the 2020 U.S. Presidential Primary Elections Across Six Search Engines

2021 ◽  
pp. 089443932110068
Author(s):  
Aleksandra Urman ◽  
Mykola Makhortykh ◽  
Roberto Ulloa
Keyword(s):  
Search Engine ◽  
Search Engines ◽  
Large Scale ◽  
Web Search ◽  
Primary Elections ◽  
Virtual Agents ◽  
Search Results ◽  
Presidential Primary ◽  
Large Scale Analysis ◽  
Algorithmic Information

We examine how six search engines filter and rank information in relation to the queries on the U.S. 2020 presidential primary elections under the default—that is nonpersonalized—conditions. For that, we utilize an algorithmic auditing methodology that uses virtual agents to conduct large-scale analysis of algorithmic information curation in a controlled environment. Specifically, we look at the text search results for “us elections,” “donald trump,” “joe biden,” “bernie sanders” queries on Google, Baidu, Bing, DuckDuckGo, Yahoo, and Yandex, during the 2020 primaries. Our findings indicate substantial differences in the search results between search engines and multiple discrepancies within the results generated for different agents using the same search engine. It highlights that whether users see certain information is decided by chance due to the inherent randomization of search results. We also find that some search engines prioritize different categories of information sources with respect to specific candidates. These observations demonstrate that algorithmic curation of political information can create information inequalities between the search engine users even under nonpersonalized conditions. Such inequalities are particularly troubling considering that search results are highly trusted by the public and can shift the opinions of undecided voters as demonstrated by previous research.

Associating Searching on Search Engines to Subsequent Searching on Sites

2016 ◽  
Vol 8 (2) ◽  
pp. 30-43
Author(s):  
Adan Ortiz-Cordova ◽  
Bernard J. Jansen
Keyword(s):  
Search Engine ◽  
Search Engines ◽  
Web Search ◽  
Research Study ◽  
Search Queries ◽  
Web Search Engine ◽  
Search Patterns ◽  
Search Information

In this research study, the authors investigate the association between external searching, which is searching on a web search engine, and internal searching, which is searching on a website. They classify 295,571 external – internal searches where each search is composed of a search engine query that is submitted to a web search engine and then one or more subsequent queries submitted to a commercial website by the same user. The authors examine 891,453 queries from all searches, of which 295,571 were external search queries and 595,882 were internal search queries. They algorithmically classify all queries into states, and then clustered the searching episodes into major searching configurations and identify the most commonly occurring search patterns for both external, internal, and external-to-internal searching episodes. The research implications of this study are that external sessions and internal sessions must be considered as part of a continuous search episode and that online businesses can leverage external search information to more effectively target potential consumers.

Web Search Engine Architectures and their Performance Analysis

2011 ◽  
pp. 491-509
Author(s):  
Xiannong Meng
Keyword(s):  
Performance Analysis ◽  
Search Engine ◽  
Search Engines ◽  
Web Search ◽  
General Purpose ◽  
Performance Measurements ◽  
Web Documents ◽  
System Architectures ◽  
Web Search Engine ◽  
And Performance

This chapter surveys various technologies involved in a Web search engine with an emphasis on performance analysis issues. The aspects of a general-purpose search engine covered in this survey include system architectures, information retrieval theories as the basis of Web search, indexing and ranking of Web documents, relevance feedback and machine learning, personalization, and performance measurements. The objectives of the chapter are to review the theories and technologies pertaining to Web search, and help us understand how Web search engines work and how to use the search engines more effectively and efficiently.

WEBCONTENT VISUALIZER: A VISUALIZATION SYSTEM FOR SEARCH ENGINES IN SEMATIC WEB

2011 ◽  
Vol 10 (05) ◽  
pp. 913-931 ◽  
Author(s):  
XIANYONG FANG ◽  
CHRISTIAN JACQUEMIN ◽  
FRÉDÉRIC VERNIER
Keyword(s):  
Semantic Web ◽  
Search Engine ◽  
Search Engines ◽  
Web Search ◽  
Search Query ◽  
Visualization System ◽  
Xml Documents ◽  
Web Search Engines ◽  
New Generation

Since the results from Semantic Web search engines are highly structured XML documents, they cannot be efficiently visualized with traditional explorers. Therefore, the Semantic Web calls for a new generation of search query visualizers that can rely on document metadata. This paper introduces such a visualization system called WebContent Visualizer that is used to display and browse search engine results. The visualization is organized into three levels: (1) Carousels contain documents with the same ranking, (2) carousels are piled into stacks, one for each date, and (3) these stacks are organized along a meta-carousel to display the results for several dates. Carousel stacks are piles of local carousels with increasing radii to visualize the ranks of classes. For document comparison, colored links connect documents between neighboring classes on the basis of shared entities. Based on these techniques, the interface is made of three collaborative components: an inspector window, a visualization panel, and a detailed dialog component. With this architecture, the system is intended to offer an efficient way to explore the results returned by Semantic Web search engines.

Rethinking gaming: The ethical work of optimization in web search engines

2019 ◽  
Vol 49 (5) ◽  
pp. 707-731 ◽  
Author(s):  
Malte Ziewitz
Keyword(s):  
Search Engine ◽  
Search Engines ◽  
Web Search ◽  
The United Kingdom ◽  
Ethical Work ◽  
Web Search Engines ◽  
The One ◽  
A Site ◽  
Shifting Boundaries ◽  
Precarious Situation

When measures come to matter, those measured find themselves in a precarious situation. On the one hand, they have a strong incentive to respond to measurement so as to score a favourable rating. On the other hand, too much of an adjustment runs the risk of being flagged and penalized by system operators as an attempt to ‘game the system’. Measures, the story goes, are most useful when they depict those measured as they usually are and not how they intend to be. In this article, I explore the practices and politics of optimization in the case of web search engines. Drawing on materials from ethnographic fieldwork with search engine optimization (SEO) consultants in the United Kingdom, I show how maximizing a website’s visibility in search results involves navigating the shifting boundaries between ‘good’ and ‘bad’ optimization. Specifically, I am interested in the ethical work performed as SEO consultants artfully arrange themselves to cope with moral ambiguities provoked and delegated by the operators of the search engine. Building on studies of ethics as a practical accomplishment, I suggest that the ethicality of optimization has itself become a site of governance and contestation. Studying such practices of ‘being ethical’ not only offers opportunities for rethinking popular tropes like ‘gaming the system’, but also draws attention to often-overlooked struggles for authority at the margins of contemporary ranking schemes.

Digital image access: an exploration of the best practices of online resources

2014 ◽  
Vol 32 (1) ◽  
pp. 98-119 ◽  
Author(s):  
Elaine Menard ◽  
Margaret Smithglass
Keyword(s):  
Best Practices ◽  
Image Retrieval ◽  
Search Engines ◽  
Research Project ◽  
Content Type ◽  
Retrieval Systems ◽  
Image Access ◽  
General Search ◽  
High Degree ◽  
Very High

Purpose – The purpose of this paper is to present the results of the first phase of a research project that aims to develop a bilingual interface for the retrieval of digital images. The main objective of this extensive exploration was to identify the characteristics and functionalities of existing search interfaces and similar tools available for image retrieval. Design/methodology/approach – An examination of 159 resources that offer image retrieval was carried out. First, general search functionalities offered by content-based image retrieval systems and text-based systems are described. Second, image retrieval in a multilingual context is explored. Finally, the search functionalities provided by four types of organisations (libraries, museums, image search engines and stock photography databases) are investigated. Findings – The analysis of functionalities offered by online image resources revealed a very high degree of consistency within the types of resources examined. The resources found to be the most navigable and interesting to use were those built with standardised vocabularies combined with a clear, compact and efficient user interface. The analysis also highlights that many search engines are equipped with multiple language support features. A translation device, however, is implemented in only a few search engines. Originality/value – The examination of best practices for image retrieval and the analysis of the real users' expectations, which will be obtained in the next phase of the research project, constitute the foundation upon which the search interface model that the authors propose to develop is based. It also provides valuable suggestions and guidelines for search engine researchers, designers and developers.

The Externalities of Search 2.0: The Emerging Privacy Threats when the Drive for the Perfect Search Engine meets Web 2.0

First Monday ◽  
2008 ◽  
Author(s):  
Michael Zimmer
Keyword(s):  
Web 2.0 ◽  
Search Engine ◽  
Search Engines ◽  
Information Seeking ◽  
Web Search ◽  
Personal Information ◽  
Informational Privacy ◽  
Capture Process ◽  
Privacy Threats ◽  
Intellectual Activities

Web search engines have emerged as a ubiquitous and vital tool for the successful navigation of the growing online informational sphere. As Google puts it, the goal is to "organize the world's information and make it universally accessible and useful" and to create the "perfect search engine" that provides only intuitive, personalized, and relevant results. Meanwhile, the so-called Web 2.0 phenomenon has blossomed based, largely, on the faith in the power of the networked masses to capture, process, and mashup one's personal information flows in order to make them more useful, social, and meaningful. The (inevitable) combining of Google's suite of information-seeking products with Web 2.0 infrastructures -- what I call Search 2.0 -- intends to capture the best of both technical systems for the touted benefit of users. By capturing the information flowing across Web 2.0, search engines can better predict users' needs and wants, and deliver more relevant and meaningful results. While intended to enhance mobility in the online sphere, this paper argues that the drive for Search 2.0 necessarily requires the widespread monitoring and aggregation of a users' online personal and intellectual activities, bringing with it particular externalities, such as threats to informational privacy while online.

Sign in / Sign up

Export Citation Format

Share Document