As the Web population continues to grow, more non-English users will be amassed online. The purpose of this chapter is to describe the methods and the criteria used for evaluating search engines and to propose a model for evaluating the searching effectiveness of Web retrieval systems in non-English queries. The qualities and weaknesses related to the handling of Greek and Italian queries are evaluated based on this method. The fundamental purpose of the methodology is to establish quality measurements on search engine utilization from the perspective of end users. Application of the proposed evaluation methodology aids users to select the most effective search engine and developers to identify some of the modules of their software that need improvements.
Key Terms in this Chapter
Search Engine: Search engines are advanced searching systems operating on hypertext collections. Search engines act both as information retrieval and data retrieval systems trying to locate Web pages, images, video, and sounds. They additionally offer a number of specialized services such as book search, blog search, maps, e-shopping, and so forth.
Precision: Precision is an information retrieval performance measure that quantifies the fraction of retrieved documents which are known to be relevant.
Lemmatization: Lemmatization involves the reduction of words to their respective lemmas. For example, the lemma for the words “computation” and “computer” is the word “compute”. Lemmatizers operate on single and compound terms and on phrases, while stemmers take as input single words only.
Stopwords: Stopwords are the common words with low discriminatory power efficient to distinguish between documents. Usual candidates of the stopword list are articles, prepositions, and conjunctions, although specific nouns, verbs, or other grammatical types could be of low importance in terms of information retrieval in specific domains.
Index: Index refers to a database containing the most important terms of each document which has been statistically analyzed by a retrieval system. Index terms or keywords contained in the index of each search engine are matched to the user query terms so as to retrieve the most relevant documents. Traditional retrieval systems keep only the terms carrying significant information in their indexes. Search engines store all the terms contained in Web pages to support “exact matching” and “all the words” queries.
Recall: Recall is an information retrieval performance measure that quantifies the fraction of known relevant documents which are effectively retrieved.
Information Retrieval: Information retrieval (IR) is the science of searching for information in documents, searching for documents themselves, searching for metadata which describe documents, or searching within hypertext collections such as the Internet or intranets. IR is further analyzed to text retrieval, document retrieval, and image, video, or sound retrieval. IR is an interdisciplinary scientific field based in computer science, library science, information science, cognitive psychology, linguistics, and statistics.
Data Retrieval: Data retrieval is the retrieval of items (objects, Web pages, documents, etc.) which satisfy specific conditions set in a regular expression like query. While IR aims at satisfying a user information need usually expressed in natural language, data retrieval aims at determining which documents contain the exact terms of the user queries.
Stemming: Stemming is the process of reducing a word to its stem or root form. For the purposes of IR, morphological variants of words have similar semantic interpretations and can be considered as equivalent. For example, the word “computation” might be stemmed to “comput”. Stemming is either based on linguistic dictionaries or on algorithms.
Query: A user query is the expression of the user information need, usually in natural language. Some retrieval systems allow the use of Boolean connectives between the query terms.