Julia Mendelsohn
@jmendelsohn2.bsky.social
Incoming Asst Prof @UMD Info College, currently postdoc @UChicago. NLP, computational social science, political communication, linguistics. Past: Info PhD @UMich, CS + Lx @Stanford. Interests: cats, Yiddish, talking to my cats in Yiddish.
Warm greeting from the DC metro upon my return from running the NLP4Democracy workshop. 🤢
October 11, 2025 at 11:10 PM
Warm greeting from the DC metro upon my return from running the NLP4Democracy workshop. 🤢
We also show that use of creature-related metaphors (animal, vermin, parasite) is associated with higher retweet counts, and the effects are actually larger for liberal authors than conservatives
February 20, 2025 at 7:59 PM
We also show that use of creature-related metaphors (animal, vermin, parasite) is associated with higher retweet counts, and the effects are actually larger for liberal authors than conservatives
Unsurprisingly, we find that conservative ideology is associated with higher metaphor use, but the extent varies across concepts.
Interestingly, authors with stronger left-wing ideologies are actually more likely to use creature-related metaphor than moderate liberals (animal, vermin, parasite).
Interestingly, authors with stronger left-wing ideologies are actually more likely to use creature-related metaphor than moderate liberals (animal, vermin, parasite).
February 20, 2025 at 7:59 PM
Unsurprisingly, we find that conservative ideology is associated with higher metaphor use, but the extent varies across concepts.
Interestingly, authors with stronger left-wing ideologies are actually more likely to use creature-related metaphor than moderate liberals (animal, vermin, parasite).
Interestingly, authors with stronger left-wing ideologies are actually more likely to use creature-related metaphor than moderate liberals (animal, vermin, parasite).
We create a new dataset of 1,600 tweets, each annotated by ~8 people for judgements of metaphor with respect to a given source domain concept to evaluate our approach. We evaluate 3 LLMs, 2 prompt variations, and show that incorporating SBERT similarity consistently improves performance.
February 20, 2025 at 7:59 PM
We create a new dataset of 1,600 tweets, each annotated by ~8 people for judgements of metaphor with respect to a given source domain concept to evaluate our approach. We evaluate 3 LLMs, 2 prompt variations, and show that incorporating SBERT similarity consistently improves performance.
We then propose and evaluate a new approach that combines word-level and document-level measures of metaphorical language, using LLMs and document embeddings (SBERT) respectively. While we focus on metaphorical dehumanization of immigrants, this method could be applied to many other contexts!
February 20, 2025 at 7:59 PM
We then propose and evaluate a new approach that combines word-level and document-level measures of metaphorical language, using LLMs and document embeddings (SBERT) respectively. While we focus on metaphorical dehumanization of immigrants, this method could be applied to many other contexts!
We first identify seven dehumanizing "source domain" concepts in immigration discourse (e.g. "water" or "vermin"). Sometimes, dehumanizing metaphors are overtly hateful, but are often accepted as natural ways of talking about immigrants (e.g. "waves of immigration").
February 20, 2025 at 7:59 PM
We first identify seven dehumanizing "source domain" concepts in immigration discourse (e.g. "water" or "vermin"). Sometimes, dehumanizing metaphors are overtly hateful, but are often accepted as natural ways of talking about immigrants (e.g. "waves of immigration").
New preprint!
Metaphors shape how people understand politics, but measuring them (& their real-world effects) is hard.
We develop a new method to measure metaphor & use it to study dehumanizing metaphor in 400K immigration tweets Link: bit.ly/4i3PGm3
#NLP #NLProc #polisky #polcom #compsocialsci
🐦🐦
Metaphors shape how people understand politics, but measuring them (& their real-world effects) is hard.
We develop a new method to measure metaphor & use it to study dehumanizing metaphor in 400K immigration tweets Link: bit.ly/4i3PGm3
#NLP #NLProc #polisky #polcom #compsocialsci
🐦🐦
February 20, 2025 at 7:59 PM
New preprint!
Metaphors shape how people understand politics, but measuring them (& their real-world effects) is hard.
We develop a new method to measure metaphor & use it to study dehumanizing metaphor in 400K immigration tweets Link: bit.ly/4i3PGm3
#NLP #NLProc #polisky #polcom #compsocialsci
🐦🐦
Metaphors shape how people understand politics, but measuring them (& their real-world effects) is hard.
We develop a new method to measure metaphor & use it to study dehumanizing metaphor in 400K immigration tweets Link: bit.ly/4i3PGm3
#NLP #NLProc #polisky #polcom #compsocialsci
🐦🐦
Here are pictures of my cat Bitsy helping with preparing both posters
November 15, 2024 at 2:47 PM
Here are pictures of my cat Bitsy helping with preparing both posters
I had a great time talking about framing and social movements at TADA 2023 last week (my third Text as Data conference!) I'm sharing my poster for those who didn't have a chance to see it in person, mainly because I need everybody to admire the top right corner.
November 14, 2023 at 3:47 PM
I had a great time talking about framing and social movements at TADA 2023 last week (my third Text as Data conference!) I'm sharing my poster for those who didn't have a chance to see it in person, mainly because I need everybody to admire the top right corner.