{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/look-whos-talking-inferring-speaker","title":"Look Who's Talking: Inferring Speaker Attributes from Personal Longitudinal Dialog","arxiv_id":"1904.11610","date":"2019-04-25","proceeding":null,"authors":["Charles Welch","Verónica Pérez-Rosas","Jonathan K. Kummerfeld","Rada Mihalcea"],"abstract":"We examine a large dialog corpus obtained from the conversation history of a\nsingle individual with 104 conversation partners. The corpus consists of half a\nmillion instant messages, across several messaging platforms. We focus our\nanalyses on seven speaker attributes, each of which partitions the set of\nspeakers, namely: gender; relative age; family member; romantic partner;\nclassmate; co-worker; and native to the same country. In addition to the\ncontent of the messages, we examine conversational aspects such as the time\nmessages are sent, messaging frequency, psycholinguistic word categories,\nlinguistic mirroring, and graph-based features reflecting how people in the\ncorpus mention each other. We present two sets of experiments predicting each\nattribute using (1) short context windows; and (2) a larger set of messages. We\nfind that using all features leads to gains of 9-14% over using message text\nonly.","url_abs":"http://arxiv.org/abs/1904.11610v1","url_pdf":"http://arxiv.org/pdf/1904.11610v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"look-whos-talking-inferring-speaker","repo_url":"https://github.com/cfwelch/longitudinal_dialog","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.11610","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}