Abstract：Which of the book recommendation sections is the most similar to the user selections in LibraryThingPurpose This study aims to determine the most similar set of recommendation books to the user selections in LibraryThingDesignmethodologyapproach For this purpose30000 tags related to History on the LibraryThing have been selectedTheir tags and the tags of the related recommended books were extracted from three different recommendations sections on LibraryThingThenfour similarity criteria of Jaccard coefficientCosine similarityDice coefficient and Pearson correlation coefficient were used to calculate the similarity between the tagsTo determine the most similar recommended sectionthe best similarity criterion had to be determined firstSoa researcher-made questionnaire was provided to History expertsFindings The results showed that the Jaccard coefficientwith a frequency of 3281is the best similarity criterion from the point of view of History expertsBesidesthe degree of similarity in LibraryThing recommendations section according to this criterion is equal to 0256in the section of books with similar library subjects and classifications is 0163 and in the Member recommendations section is 0152Based on the findings of this studythe LibraryThing recommendations section has succeeded in introducing the most similar books to the selected book compared to the other two sectionsOriginalityvalue To the best of the authorsknowledgeitis for the first timethree sections of LibraryThing recommendations are compared by four different similarity criteria to show which sections would be more beneficial for the user browsingThe results showed that machine recommendations work better than humansRetrieval and IndexingProvide more accurate book recommendations with similarity calculationsConsulting ServiceThrough AI recommendationsusers can get books that are more in line with their interests and needsThis research mainly uses data exploration technologies to calculate the similarity between labels through four similar standardsCosine SimilitiesDICE COEFFINTand Pearson Correlation Coefficient to determine which part of the book recommendations are selected from usersBooks are the most similarIn this wayresearching which recommendation method can best meet the needs of users