{"response":{"docs":[{"system_create_dtsi":"2021-05-14T20:12:58Z","system_modified_dtsi":"2021-05-14T20:13:13Z","has_model_ssim":["Dataset"],"id":"pv63g177p","accessControl_ssim":["8c475b25-ba32-4062-9e44-ed78150ef3bd"],"depositor_ssim":["mccabeen@ucmail.uc.edu"],"depositor_tesim":["mccabeen@ucmail.uc.edu"],"title_tesim":["Vocabulary Count Feature Vectors for Medical School Classifier "],"date_uploaded_dtsi":"2021-05-14T20:12:58Z","date_modified_dtsi":"2021-05-14T20:12:58Z","isPartOf_ssim":["admin_set/default"],"geo_subject_tesim":["Cincinnati, Ohio"],"time_period_tesim":["2010-2019"],"college_tesim":["Libraries"],"department_tesim":["Digital Scholarship Center (DSC)"],"creator_tesim":["Boylan, Andrew","McCabe, Erin E."],"publisher_tesim":["University of Cincinnati"],"subject_tesim":["Medicine"],"language_tesim":["English"],"description_tesim":["Classifier algorithms use the features (collectively known as Feature Vectors) of each item in a dataset to assess the classification to which that item belongs. \r\n\r\nIn this classifier approach, each item represents one document containing the application essay combined with unstructured language describing relevant activities of a single applicant. For privacy, the full text of this document is not provided. Instead, each document is represented only by its features. The feature vector for this classifier is based on the term frequency for each of the identified terms. E.G. Doc_A contains 0 occurrences of any terms identified as family medicine vocabulary, and 10 occurrences of terms from the the non-family-medicine vocabulary. "],"license_tesim":["http://www.opendatacommons.org/licenses/pddl/1.0/"],"thumbnail_path_ss":"/assets/work-ff055336041c3f7d310ad69109eda4a887b16ec501f35afc0a547c4adb97ee72.png","suppressed_bsi":false,"actionable_workflow_roles_ssim":["admin_set/default-default-depositing"],"workflow_state_name_ssim":["deposited"],"member_of_collections_ssim":["Use of Medical School Applications to Identify Potential Interest in Family Medicine​"],"member_of_collection_ids_ssim":["ws859h17t"],"visibility_ssi":"open","admin_set_tesim":["Default Admin Set"],"sort_title_ssi":"VOCABULARY COUNT FEATURE VECTORS FOR MEDICAL SCHOOL CLASSIFIER ","human_readable_type_tesim":["Dataset"],"read_access_group_ssim":["public"],"edit_access_group_ssim":["admin"],"edit_access_person_ssim":["mccabeen@ucmail.uc.edu"],"nesting_collection__ancestors_ssim":["ws859h17t"],"nesting_collection__parent_ids_ssim":["ws859h17t"],"nesting_collection__pathnames_ssim":["ws859h17t/pv63g177p"],"nesting_collection__deepest_nested_depth_isi":2,"_version_":1699766017091174400,"timestamp":"2021-05-14T20:13:14.400Z","score":0.00049999997},{"system_create_dtsi":"2021-05-14T19:50:31Z","system_modified_dtsi":"2021-05-14T19:51:05Z","has_model_ssim":["Dataset"],"id":"kw52j9497","accessControl_ssim":["e0ebf0df-2609-4b62-8b6d-448da8000169"],"depositor_ssim":["mccabeen@ucmail.uc.edu"],"depositor_tesim":["mccabeen@ucmail.uc.edu"],"title_tesim":["Vocabulary Comparison of Medical School Applications"],"date_uploaded_dtsi":"2021-05-14T19:50:30Z","date_modified_dtsi":"2021-05-14T19:50:30Z","isPartOf_ssim":["admin_set/default"],"geo_subject_tesim":["Cincinnati, Ohio"],"time_period_tesim":["2010-2019"],"college_tesim":["Libraries"],"department_tesim":["Digital Scholarship Center (DSC)"],"creator_tesim":["McCabe, Erin E."],"publisher_tesim":["University of Cincinnati"],"subject_tesim":["Medicine"],"language_tesim":["English"],"description_tesim":["W2V takes terms from a large corpus of text and models them onto a vector space, based on word associations from your dataset. These Word Associations take into account each word's immediate context (its ten neighboring words).​\r\n\r\nFollowing the data modeling (large-scale unstructured text), The platform then generates a visualization of this vector space, which lets us perform analysis e.g. detect synonymous/synonym-ish words and highlight related words. At the heart of this project, is W2V's ability to identify key words that were more frequent - and more unique - to each group using results from 2 different W2V models – one for each group's application texts.​\r\n\r\nWe coded these Key Terms into categories, then analyzed those categories for overarching themes.​\r\n\r\n​"],"license_tesim":["http://www.opendatacommons.org/licenses/pddl/1.0/"],"thumbnail_path_ss":"/assets/work-ff055336041c3f7d310ad69109eda4a887b16ec501f35afc0a547c4adb97ee72.png","suppressed_bsi":false,"actionable_workflow_roles_ssim":["admin_set/default-default-depositing"],"workflow_state_name_ssim":["deposited"],"member_of_collections_ssim":["Use of Medical School Applications to Identify Potential Interest in Family Medicine​"],"member_of_collection_ids_ssim":["ws859h17t"],"visibility_ssi":"open","admin_set_tesim":["Default Admin Set"],"sort_title_ssi":"VOCABULARY COMPARISON OF MEDICAL SCHOOL APPLICATIONS","human_readable_type_tesim":["Dataset"],"read_access_group_ssim":["public"],"edit_access_group_ssim":["admin"],"edit_access_person_ssim":["mccabeen@ucmail.uc.edu"],"nesting_collection__ancestors_ssim":["ws859h17t"],"nesting_collection__parent_ids_ssim":["ws859h17t"],"nesting_collection__pathnames_ssim":["ws859h17t/kw52j9497"],"nesting_collection__deepest_nested_depth_isi":2,"_version_":1699764624734289920,"timestamp":"2021-05-14T19:51:06.545Z","score":0.00049999997}],"facets":[{"name":"human_readable_type_sim","items":[{"value":"Dataset","hits":2,"label":"Dataset"}],"label":"Human Readable Type Sim"},{"name":"creator_sim","items":[{"value":"McCabe, Erin E.","hits":2,"label":"McCabe, Erin E."},{"value":"Boylan, Andrew","hits":1,"label":"Boylan, Andrew"}],"label":"Creator Sim"},{"name":"subject_sim","items":[{"value":"Medicine","hits":2,"label":"Medicine"}],"label":"Subject Sim"},{"name":"college_sim","items":[{"value":"Libraries","hits":2,"label":"Libraries"}],"label":"College Sim"},{"name":"department_sim","items":[{"value":"Digital Scholarship Center (DSC)","hits":2,"label":"Digital Scholarship Center (DSC)"}],"label":"Department Sim"},{"name":"language_sim","items":[{"value":"English","hits":2,"label":"English"}],"label":"Language Sim"},{"name":"publisher_sim","items":[{"value":"University of Cincinnati","hits":2,"label":"University of Cincinnati"}],"label":"Publisher Sim"},{"name":"date_created_sim","items":[],"label":"Date Created Sim"},{"name":"member_of_collection_ids_ssim","items":[{"value":"ws859h17t","hits":2,"label":"ws859h17t"}],"label":"Member Of Collection Ids Ssim"},{"name":"generic_type_sim","items":[{"value":"Work","hits":2,"label":"Work"}],"label":"Generic Type Sim"}],"pages":{"current_page":1,"next_page":null,"prev_page":null,"total_pages":1,"limit_value":10,"offset_value":0,"total_count":2,"first_page?":true,"last_page?":true}}}