{"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/words-are-malleable-computing-semantic-shifts","title":"Words are Malleable: Computing Semantic Shifts in Political and Media Discourse","arxiv_id":"1711.05603","date":"2017-11-15","proceeding":null,"authors":["Hosein Azarbonyad","Mostafa Dehghani","Kaspar Beelen","Alexandra Arkut","Maarten Marx","Jaap Kamps"],"abstract":"Recently, researchers started to pay attention to the detection of temporal\nshifts in the meaning of words. However, most (if not all) of these approaches\nrestricted their efforts to uncovering change over time, thus neglecting other\nvaluable dimensions such as social or political variability. We propose an\napproach for detecting semantic shifts between different viewpoints--broadly\ndefined as a set of texts that share a specific metadata feature, which can be\na time-period, but also a social entity such as a political party. For each\nviewpoint, we learn a semantic space in which each word is represented as a low\ndimensional neural embedded vector. The challenge is to compare the meaning of\na word in one space to its meaning in another space and measure the size of the\nsemantic shifts. We compare the effectiveness of a measure based on optimal\ntransformations between the two spaces with a measure based on the similarity\nof the neighbors of the word in the respective spaces. Our experiments\ndemonstrate that the combination of these two performs best. We show that the\nsemantic shifts not only occur over time, but also along different viewpoints\nin a short period of time. For evaluation, we demonstrate how this approach\ncaptures meaningful semantic shifts and can help improve other tasks such as\nthe contrastive viewpoint summarization and ideology detection (measured as\nclassification accuracy) in political texts. We also show that the two laws of\nsemantic change which were empirically shown to hold for temporal shifts also\nhold for shifts across viewpoints. These laws state that frequent words are\nless likely to shift meaning while words with many senses are more likely to do\nso.","url_abs":"http://arxiv.org/abs/1711.05603v1","url_pdf":"http://arxiv.org/pdf/1711.05603v1.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":"words-are-malleable-computing-semantic-shifts","repo_url":"https://github.com/MLBurnham/word_embeddings","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}