The aim of this Master’s thesis is to examine the retrieval performance of two search engines, Yahoo! News and Sesam, specialized on indexing news articles in Swedish. Thirty search questions were used in this study, divided into three different categories: domestic news, amusement and sport. Precision has been calculated both for the 30 search questions as a total and for the three categories as well. Precision was calculated at every DCV-level and then divided with the number of search questions used, in an attempt to reach an average measure. An analysis was also used were precision was calculated over all the DCV-levels for each question in attempt to see how the search engines perform for a given search question and a given search engine. The relevance of the top 10 retrieved documents was judged using a binary scale. The result of the study shows little difference in precision between the two search engines. Yahoo! News performs slightly better than Sesam in most cases. The results show much variation between the search engines regarding how they perform per given search question. Much of the underlying techniques used by the search engines is not know for the public why the methods used in the study, for example the terms chosen as search terms, choice of highest DCV-level et cetera, and how these different choices made may had an impact on the result in the study is discussed rather than underlying technical functions. / Uppsatsnivå: D

The purpose of this study is to examine the retrieval performance of three search engines, specialized in retrieving news articles: News Index, Excite News Search and Ananova. Thirty questions, grouped into three categories – politics, economy and sports, were used and the first twenty documents for each question were examined. The questions used were designed to be as current as possible and efforts were made to perform the searches with as little time span as possible between each search engine. The precision of the search engines was determined for each of the questions as well as for each category and for the combined categories. In measuring precision an average was calculated, intended to favour search engines that place its relevant documents early in the ranked list. The relevance of the retrieved documents was evaluated using a three-grade scale. Irrelevant articles and duplicates were given 0 points, partially relevant documents were given 0,5 points and those judged to be highly relevant were given 1 point. The results of the study show surprisingly high precision from two of the search engines, Excite and News Index with the former performing slightly better than the latter. Ananova performed considerably worse than the other two. One possible reason for the high precision observed is the relatively low complexity of the documents retrieved compared to web pages in general. When comparing the different categories of questions one notable result was that all search engines performed considerably worse in the "economy"-category. Possible reasons for this are, apart from a higher number of duplicates, a shortage of relevant articles for the questions in this category as well as possible differences between either the documents retrieved in the different categories, or the web pages publishing them. / Uppsatsnivå: D

The purpose of this thesis is to evaluate three web-based search engines and compare the 10 first retrieved documents. We used the search engines Google, Yahoo! and Exalead. The evaluation is based upon 20 topics with strong polarized opinions and these have been derived from Swedish media and every day life. From these topics we have constructed the 20 queries used for searching. The 10 first documents are each placed in four different categories, For, Against, Neutral or Irrelevant. For and Against are opposed to each other regarding different opinions in the 20 topics. The purpose of this is to get a picture of the different topics, seen through the three search engines. Does one of the categories weigh more heavily than the other, represented in the 10 first documents? If this is the case, does the same category weigh more heavily in all three search engines, or how do they deviate from each other? The results showed that one of the categories, in most of the topics, weighs more heavily than the opposed category. The opposed category is in some cases not represented at all in the 10 first documents. In some of the topics, the same category weighs over in all three search engines, but in more than half of the topics the different search engines deviate from each other regarding the opposed categories. / Uppsatsnivå: D

The purpose of this Master’s thesis is to evaluate three general query-based web search engines. The search engines chosen are Google, Yahoo! and Live Search. The topics, which where transformed into twenty queries, are based on real users’ information needs, taken from an ask-a-question service. For every search the first 10 hits in each of the three search engines were evaluated. The measures that have been used are precision and overlap. The queries were evaluated on a binary relevance scale with 0 or 1. Precision has been measured as average precision over 1-10 DCV levels for all 20 queries in the evaluation. It has also been measured as average precision in a query-by-query calculation over 10 DCV levels for each query and search engine. The number of duplicate links, dead links, mirror pages, relevant hits and irrelevant hits has also been recorded in the study for each search engine, for a comparison. Overlap was measured at two different DCVs, 1 and 5. Eventually the results show that Google had the best results regarding precision. It also had the highest number of relevant hits. Google and Yahoo! showed the highest overlap at DCV 1. At DCV 5 the greatest overlap was between Yahoo! and Live Search. / Uppsatsnivå: D

The purpose of this paper is to compare the three search engines Web of Science, Google Scholar and MEDLINE in regards of recovery efficiency and the overlap of relevant documents when it comes to information searching for academic purposes. Furthermore, it raises the question whether freely available search engines and licensed search engines are interchangeable with each other. The empirical data in this study were collected through searches conducted in the three search engines Web of Science, Google Scholar and MEDLINE. Twenty search queries were used and the first twenty retrieved documents for each query were examined for relevance using previously designed criteria. The documents were scored by a binary relevancy scale and thereafter a precision value for each search engine was calculated. The overlap of retrieved relevant document in all three search engines were also calculated using Jaccard’s Index. The results of this study showed that Web of Science was the search engine that had the highest precision value, 0.346 and that the largest overlap was between MEDLINE and Web of Science with a value of 0.112. / Program: Bibliotekarie