Myriad- a Novel User Feedback Based Metasearch Engine

Result merging is a key component in a metasearch engine. Once the results from various search engines are collected, the metasearch system merges them into a single ranked list. The effectiveness of a metasearch engine is closely related to the result merging algorithm it employs. In this paper, we investigate a variety of resulting merging algorithms based on a wide range of available information about the retrieved results, from their local ranks, their titles and snippets, to the full documents of these results. The effectiveness of these algorithms is then compared experimentally based on 50 queries from the TREC Web track and 10 most popular general-purpose search engines. Our experiments yield two important results. First, simple result merging strategies can outperform Google. Second, merging based on the titles and snippets of retrieved results can outperform that based on the full documents.

Several users use metasearch engines directly or indirectly to access and gather data from more than one data sources. The effectiveness of a metasearch engine is majorly determined by the quality of the results and it returns and in response to user queries. The rank aggregation methods which have been proposed until now exploits very limited set of parameters such as total number of used resources and the rankings they achieved from each individual resource. In this work, we use the neural network to merge the score computation module effectively. Initially, we give a query to different search engines and the top n list from each search engine is chosen for further processing our technique. We then merge the top n list based on unique links and we do some parameter calculations such as title based calculation, snippet based calculation, content based calculation, domain calculation, position calculation and co-occurrence calculation. We give the solutions of the calculations with user given ranking of links to the neural network to train the system. The system then rank and merge the links we obtain from different search engines for the query we give. Experimentation results reports a retrieval effectiveness of about 80%, precision of about 79% for user queries and about 72% for benchmark queries. The proposed technique also includes a response time of about 76 ms for 50 links and 144 ms for 100 links.

The existing search engines return the whole web pages as the search results, which make user spend extra time to read the useless information before finding the information they really want. We propose a novel search engine model called “Component Search Engine”, which can return the contents satisfying user's query rather than the whole pages. For achieving the purpose, we adopt a Tree-View interface to display the results. Through usability study, we determinate that Component Search Engine using Tree-View interface can improve user's searching experience and efficiency.

Random walk based rank aggregation to improving web search

Supporting metasearch with XSL

A metasearch engine is a system, which is connected to different search engines. In response to a user query, it invokes suitable search engines for the query, merges the information returned by these search engines and output the merged result. There are two types of metasearch engines: one type for unstructured data (mostly text) and the other for structured data. In comparison to a text search engine, a metasearch engine can have a higher coverage of the Web and can have more timely information. A metasearch engine for structured data facilitates comparison shopping and services and is convenient to use. In this talk, we discuss the problems and their potential solutions. In addition, challenges and unsolved problems are sketched.

Frequently a user's information needs are stored in the databases of multiple search engines. It is inconvenient and inefficient for an ordinary user to invoke multiple search engines and identify useful documents from the returned results. To support unified access to multiple search engines, a metasearch engine can be constructed. When a metasearch engine receives a query from a user, it invokes the underlying search engines to retrieve useful information for the user. Metasearch engines have other benefits as a search tool such as increasing the search coverage of the Web and improving the scalability of the search. In this article, we survey techniques that have been proposed to tackle several underlying challenges for building a good metasearch engine. Among the main challenges, the database selection problem is to identify search engines that are likely to return useful documents to a given query. The document selection problem is to determine what documents to retrieve from each identified search engine. The result merging problem is to combine the documents returned from multiple search engines. We will also point out some problems that need to be further researched.

Traditional information retrieval systems are evaluated with the assumption that each query is independent. However, during their interactions with search engines, many users find themselves reformulating their queries in order to satisfy their information need. In this paper, we investigate the impact of using ranking aggregation in the context of session information retrieval. First, we identify useful sources for terms to be used as related queries. For each query, we generate related queries from various sources and use those multiple representations of a query to obtain several rankings that we combine using simple rank aggregation methods. We compare the effects of using each source and show that some sources can provide up to 46% increase in nDCG@10 over our dirichlet-smoothed language model baseline and our best result is competitive with all TREC Session track systems for 2011 and 2012.KeywordsSession SearchRanking AggregationRelevance FeedbackDiversity RetrievalRetrieval Models

Normally, statistical methods are used to generate rankings for genes in terms of their ability to distinguish between normal and malignant tumors from a gene expression dataset. However, different statistical methods yield different ranks for same gene and there is no universally accepted method for ranking. Therefore rank aggregation is required to find the overall ranking of the set of genes. There are various rank aggregation methods in the existing literature to integrate the rankings produced by various statistical tests. Moreover, the problem of integration of some partial rankings, containing unequal numbers of genes, is more challenging. In this article, a multiobjective genetic algorithm based rank aggregation method is proposed to integrate some partial rankings in an unbiased way. The first objective is to minimize the total distance from the reference ranking to the input rankings. For distance calculation, the Scaled Footrule Distance is used. The second objective is to minimize the standard deviation among those distances in order to avoid bias toward a particular input ranking. The proposed method is applied on some real-life microarray gene expression datasets, and the performance of it is compared with that of several existing rank aggregation techniques with respect to accuracy and the AUC (Area under ROC curve) value. Again, for real-life datasets, accuracy is plotted for visual comparison.

This paper presents novel approaches for combining re-ranking and rank aggregation methods aiming at improving the effectiveness of Content-Based Image Retrieval (CBIR) systems. Given a query image as input, CBIR systems retrieve the most similar images in a collection by taking into account image visual properties. In this scenario, accurately ranking collection images is of great relevance. Aiming at improving the effectiveness of CBIR systems, re-ranking and rank aggregation algorithms have been proposed. However, different re-ranking and rank aggregation approaches, applied to different image descriptors, may produce different and complementary image rankings. In this paper, we present four novel approaches for combining these rankings aiming at obtaining more effective results. Several experiments were conducted involving shape, color, and texture descriptors. The proposed approaches are also evaluated on multimodal retrieval tasks, considering visual and textual descriptors. Experimental results demonstrate that our approaches can improve significantly the effectiveness of image retrieval systems.

Discriminating meta-search: a framework for evaluation

The meta search engine is a research hotspot in the next generation search engine. Most of the results returned from the search engines we have now are irrelevant and undesirable. This paper introduces ontology into the meta search engine, and advances two methods to improve the search engine technology. The one is the expansion of the query, and the other is the personalized ontology. A new personalized meta search engine (PMSE) is built and the practical research results form the PMSE prove the efficiency and accuracy of them.

Search engines are turning out to be the greatest tools for gaining valuable data from the internet. Search engines return the search result to the user query which can be an important result or non-important result. Because, the users naturally look only at the first few pages of search results, and search engine ranking can introduce significant bias to their understanding of the internet and their information gain. When a search query is delivered to several search engines, each individual returns a list of pages based on the ranking. Scientists have confirmed that merging search results in a meta-search engine makes a substantial progress in a search result. Current meta-search engines use several search engines for fetching the results but do not emphasize on the semantic relation of the query for finding the best result. In order tod overcome this limitation, a new approach is proposed. The proposed approach can optimize meta-search results using the combination of linear search and semantic search.

Summary: This work provides a methodology to analyze user preferences regarding the components that a judicial search engine should include. We validate this methodology by developing a search system. Starting from initial characteristics, we designed a search prototype. A test was then applied to identify whether the search engine meets the user's needs. The prototype developed was compared to other next-generation search engines in terms of user satisfaction and accuracy. The results show that our proposal outperforms other search engines. Objective: Define and implement the components for the development of a judicial search engine. Methodology: The methodology consists of in: Definition: Includes a review of the state of the art of the technologies associated with the project. Prototype development: Different modules and components of the system are developed here. Evaluation: focused on usability and user satisfaction. Results: The characteristics and elements necessary for the search engine were identified. To this end, Benchmarking on general aspects and components of jurisprudence search engines was carried out. Additionally, a survey was conducted with 79 legal experts. Finally, a use test was carried out. Conclusions: A prototype of the search engine was designed according to the characteristics declared by the users. This prototype showed optimal usability and navigation because it was designed considering the needs of the user's jurisprudence. Its interfaces are easy to understand and its filters make the search process more agile and precise. Finally, the developed search engine offers a good experience to the users.

Rank aggregation is the process of aggregating multiple base rankers into a single but more comprehensive ranker, which plays an important role in many domains such as recommender system, meta-search, database, genomics, etc. Works related to the comparison of rank aggregation methods all don't have a suitable and general data generation mechanism to produce data with various characteristics and lack a more reasonable and effective algorithm evaluation performance index.Therefore, this paper presents a general data generation mechanism based on Mallows model to produce synthetic controllable datasets, uses generalized Kendall rank correlation coefficient and rank-biased overlap to evaluate and compare the performance of two kinds of methods under different settings.Besides, we also consider the comparison between indices and the impact of data characteristics on the algorithms.This paper may be helpful to researchers and decision-makers from multiple domains.