{"id":632,"date":"2017-05-30T10:30:02","date_gmt":"2017-05-30T14:30:02","guid":{"rendered":"http:\/\/wwp.northeastern.edu\/blog\/?p=632"},"modified":"2017-07-24T16:17:50","modified_gmt":"2017-07-24T20:17:50","slug":"word-vector-analysis-project","status":"publish","type":"post","link":"https:\/\/wwp.northeastern.edu\/blog\/word-vector-analysis-project\/","title":{"rendered":"The WWP Begins Research into Word Vector Analysis"},"content":{"rendered":"<p><span style=\"font-weight: 400;\">We are thrilled to announce that the Women Writers Project has begun work on a new project \u201cWord Vector Analysis for TEI\/XML: A user-Friendly Toolkit,\u201d funded under a <a href=\"http:\/\/www.northeastern.edu\/resdev\/resources\/internal-grants\/tier-1-seed-grantproof-of-concept-program\/fy18-tier-1-grant-recipients\/\">Tier 1 grant<\/a> from Northeastern University, awarded to project co-PIs, professors Julia Flanders, Elizabeth Dillon, and Cody Dunne.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">\u201cWord Vector Analysis for TEI\/XML\u201d brings together two major digital humanities methodologies: text encoding and text analysis, as we aim to develop an exploratory web interface as part of the <\/span><a href=\"http:\/\/www.wwp.northeastern.edu\/wwo\/lab\/\"><span style=\"font-weight: 400;\">WWO Lab<\/span><\/a><span style=\"font-weight: 400;\">, which will allow users to visualize vector-space models with data from the <\/span><a href=\"http:\/\/www.wwp.northeastern.edu\/wwo\/\"><span style=\"font-weight: 400;\">Women Writers Online<\/span><\/a><span style=\"font-weight: 400;\"> (WWO) TEI corpus and its sister corpus from the <\/span><a href=\"http:\/\/webapp1.dlib.indiana.edu\/vwwp\/\"><span style=\"font-weight: 400;\">Victorian Women Writers Project<\/span><\/a><span style=\"font-weight: 400;\"> (VWWP). For this collaborative project, a team of faculty, graduate students, and WWP staff will develop mechanisms to transform TEI documents for analysis with word embedding models, using the WWO\/VWWP corpus as a test case. We will also publish a prototype web interface for exploring these models. The interface will enable users to input terms of interest and discover similar terms, locate analogies, and explore thematic clusters of terms. The WWP is especially suited to this type of text analysis because of our collection of TEI-encoded documents that are information-rich and relatively free from digitization errors. We will thus be able to create text-analysis-friendly data from TEI documents without losing the significant informational content of the markup.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Our prototype will integrate the word2vec text analysis tool using skip-gram negative sampling, as well as other experimental word vector model training methods, into an information pipeline that takes in TEI\/XML data, performs a variety of preliminary processing steps taking advantage of information in the markup, passes the resulting text file on for analysis, and then sends the results to an appropriate visualization tool. The user interface will enable users to make selections based on information in the markup (e.g., to analyze texts within a certain time period or of a certain genre, or to focus on specific textual components such as background narration or direct speech), and to choose the visualization options for the output. The tool set will take advantage of TEI markup to improve tokenization in text analysis (for example, encoding with &lt;orgName&gt; removes any ambiguity about whether the string \u201cMassachusetts Historical Society\u201d refers to a single organization) and to enable comparison within corpora based on the semantic features represented by the markup. The prototype will initially focus on word vector analysis, but other text analysis routines such as topic modeling could be included as options in the pipeline as well.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">As we move forward in our research, we will be publishing use cases and sample research projects using the word2vec text analysis tool. For example, a scholar of early American literature might be interested in the ways in which \u201cAmerica\u201d as a concept is represented in early women\u2019s writing. Using our tool on the WWO\/VWWP corpus, she may start by finding words that are nearest to words like \u201cAmerica,\u201d \u201cEngland,\u201d \u201ccountry,\u201d and \u201cnation.\u201d Or, she might test out the analogy function (such as in the often cited [king] &#8211; [man] + [woman] = [queen] word2vec example), experimenting with relationships between words like \u201cEngland\u201d and \u201cNew England\u201d or \u201cVirginia\u201d and \u201cMassachusetts\u201d. \u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">For further reading on word embedding models and word2vec, we\u2019ve provided some suggested blog posts below:<\/span><\/p>\n<p><span style=\"font-weight: 400;\">\u201c<\/span><a href=\"http:\/\/bookworm.benschmidt.org\/posts\/2015-10-25-Word-Embeddings.html\"><span style=\"font-weight: 400;\">Vector Space Models for the Digital Humanities<\/span><\/a><span style=\"font-weight: 400;\">\u201d by Ben Schmidt <\/span><\/p>\n<p><span style=\"font-weight: 400;\">\u201c<\/span><a href=\"http:\/\/www.ghostweather.com\/files\/word2vecpride\/\"><span style=\"font-weight: 400;\">Pride and Prejudice and Word Embedding Distance<\/span><\/a><span style=\"font-weight: 400;\">\u201d by Lynn Cherny<\/span><\/p>\n<p><span style=\"font-weight: 400;\">\u201c<\/span><a href=\"http:\/\/ryanheuser.org\/word-vectors-1\/\"><span style=\"font-weight: 400;\">Word Vectors in the Eighteenth Century<\/span><\/a><span style=\"font-weight: 400;\">\u201d by Ryan Heuser <\/span><\/p>\n<p><span style=\"font-weight: 400;\">\u201c<a href=\"http:\/\/www.twonewthings.com\/gabrielrecchia\/2016\/06\/11\/numberless-degrees-of-similitude-word-vectors\/\">Numberless Degrees of Similitude\u201d: A Response to Ryan Heuser&#8217;s \u2018Word Vectors in the Eighteenth Century, Part 1<\/a>\u2019\u201d by\u00a0Gabriel Recchia<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>We are thrilled to announce that the Women Writers Project has begun work on a new project \u201cWord Vector Analysis for TEI\/XML: A user-Friendly Toolkit,\u201d funded under a Tier 1 grant from Northeastern University, awarded to project co-PIs, professors Julia Flanders, Elizabeth Dillon, and Cody Dunne. \u201cWord Vector Analysis for TEI\/XML\u201d brings together two major digital humanities methodologies: text encoding and text analysis, as we aim to develop an exploratory web interface as part of the WWO Lab, which will&#8230;<\/p>\n<p class=\"read-more\"><a class=\"btn btn-default\" href=\"https:\/\/wwp.northeastern.edu\/blog\/word-vector-analysis-project\/\"> Read More<span class=\"screen-reader-text\">  Read More<\/span><\/a><\/p>\n","protected":false},"author":7,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[18,76],"tags":[],"class_list":["post-632","post","type-post","status-publish","format-standard","hentry","category-announcements","category-text-analysis"],"_links":{"self":[{"href":"https:\/\/wwp.northeastern.edu\/blog\/wp-json\/wp\/v2\/posts\/632","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wwp.northeastern.edu\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wwp.northeastern.edu\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wwp.northeastern.edu\/blog\/wp-json\/wp\/v2\/users\/7"}],"replies":[{"embeddable":true,"href":"https:\/\/wwp.northeastern.edu\/blog\/wp-json\/wp\/v2\/comments?post=632"}],"version-history":[{"count":6,"href":"https:\/\/wwp.northeastern.edu\/blog\/wp-json\/wp\/v2\/posts\/632\/revisions"}],"predecessor-version":[{"id":643,"href":"https:\/\/wwp.northeastern.edu\/blog\/wp-json\/wp\/v2\/posts\/632\/revisions\/643"}],"wp:attachment":[{"href":"https:\/\/wwp.northeastern.edu\/blog\/wp-json\/wp\/v2\/media?parent=632"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wwp.northeastern.edu\/blog\/wp-json\/wp\/v2\/categories?post=632"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wwp.northeastern.edu\/blog\/wp-json\/wp\/v2\/tags?post=632"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}