

{"id":47,"date":"2026-11-16T19:39:51","date_gmt":"2026-11-17T00:39:51","guid":{"rendered":"https:\/\/sites.temple.edu\/yaqihu\/?p=47"},"modified":"2026-11-16T19:39:51","modified_gmt":"2026-11-17T00:39:51","slug":"12-semantic-distance","status":"publish","type":"post","link":"https:\/\/sites.temple.edu\/yaqihu\/2026\/11\/16\/12-semantic-distance\/","title":{"rendered":"#12 Semantic distance"},"content":{"rendered":"\n<p>Reilly et al. (2023) study how the relationships between neighboring words can help describe the flow of ideas through a text. Their method measures the semantic distance between consecutive content words using two representations of word meaning, one based on human ratings of experiential features and the other on patterns of word use in written English. In a simulated word-list task, both measures detected transitions between categories such as animals and musical instruments. In Jack London\u2019s <em>To Build a Fire<\/em>, words paired in their original order were more closely related than randomly paired words, especially with the measure based on written English. The study gives researchers a way to examine where a text stays with related ideas and where it shifts as the narrative unfolds.<\/p>\n\n\n\n<p>This article gives me a way to explore how players move from describing what happened in my magic game to trying to explain it. A player might write, \u201cI thought the game only registered clicks. Then it showed the symbol I had been looking at.\u201d The relationship between those sentences tells us which expectation the reveal challenged. If the player adds, \u201cMaybe it used the camera, but I couldn\u2019t tell what it was measuring,\u201d they also identify a specific gap in their explanation. Semantic distance could help me explore where accounts shift from describing the reveal to proposing a cause. I would pair it with close reading, because two sentences can use similar words while expressing very different degrees of certainty. This connects to my central research question about how LLMs recognize and use people\u2019s uncertainty when interpreting their explanations.<\/p>\n\n\n\n<p>The feedback from this week\u2019s check-in and workshop was to keep my current storyline and start bringing it to life visually. I took the main advice to be that I should get a complete version working before trying to perfect every details. That gives me a way to move forward with the story and see how the scenes work together.<\/p>\n\n\n\n<p>I\u2019m meeting with my committee chair this week and plan to confirm the next deliverable then. My immediate production milestone is a first animated version of a short sequence from the game. I\u2019ve designed the 2D character and am ready to start animating this week. On the research side, I\u2019ve narrowed the language question to how players express what they expected, what they observed, and what they still can\u2019t explain. I\u2019d like to discuss how to capture those distinctions in the retelling and follow-up questions.<\/p>\n\n\n\n<p><strong>Reference<\/strong><\/p>\n\n\n\n<p>Reilly, J., Finley, A. M., Litovsky, C. P., &amp; Kenett, Y. N. (2023). Bigram semantic distance as an index of continuous semantic flow in natural language: Theory, tools, and applications. <em>Journal of Experimental Psychology: General, 152<\/em>(9), 2578\u20132590. <a href=\"https:\/\/doi.org\/10.1037\/xge0001389\">https:\/\/doi.org\/10.1037\/xge0001389<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Reilly et al. (2023) study how the relationships between neighboring words can help describe the flow of ideas through a text. Their method measures the semantic distance between consecutive content words using two representations of word meaning, one based on human ratings of experiential features and the other on patterns of word use in written &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/sites.temple.edu\/yaqihu\/2026\/11\/16\/12-semantic-distance\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;#12 Semantic distance&#8221;<\/span><\/a><\/p>\n","protected":false},"author":38046,"featured_media":0,"comment_status":"open","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"footnotes":""},"categories":[1],"tags":[],"class_list":["post-47","post","type-post","status-publish","format-standard","hentry","category-uncategorized","entry"],"_links":{"self":[{"href":"https:\/\/sites.temple.edu\/yaqihu\/wp-json\/wp\/v2\/posts\/47","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sites.temple.edu\/yaqihu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sites.temple.edu\/yaqihu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/sites.temple.edu\/yaqihu\/wp-json\/wp\/v2\/users\/38046"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.temple.edu\/yaqihu\/wp-json\/wp\/v2\/comments?post=47"}],"version-history":[{"count":1,"href":"https:\/\/sites.temple.edu\/yaqihu\/wp-json\/wp\/v2\/posts\/47\/revisions"}],"predecessor-version":[{"id":48,"href":"https:\/\/sites.temple.edu\/yaqihu\/wp-json\/wp\/v2\/posts\/47\/revisions\/48"}],"wp:attachment":[{"href":"https:\/\/sites.temple.edu\/yaqihu\/wp-json\/wp\/v2\/media?parent=47"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sites.temple.edu\/yaqihu\/wp-json\/wp\/v2\/categories?post=47"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sites.temple.edu\/yaqihu\/wp-json\/wp\/v2\/tags?post=47"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}