A Self-Assessing Compilation Based Search Approach for Analytical Research and Data Retrieval
by Ananth Goyal
Category: STEM
Abstract – Whenever meta-analytic research is conducted, sifting through the sheer amount of sources made available through individual databases and search engines can be time-consuming and often degrades the specificity to which sources are analyzed. This study sought to predict the feasibility of a research oriented searching algorithm across all subjects and a searching technique to counter flaws in dealing with large datasets by automating three key components of meta-analysis (a query-based search associated with the intended research topic, selecting given sources and determining their relevance to the original query, and extracting applicable information including excerpts and citations) A prototype algorithm was tested using 5 key historical queries, and results were broken down into the total number of relevant sources retrieved, the algorithm’s efficiency, the total time it takes complete one cycle, and the quality of the extracted sources. On average, the program collected a total of 126 reputable sources per search with an average efficiency of 19.55 sources per second suggesting that an algorithm built across all subject areas can make strides in future research methods.