Many social science questions ask how linguistic properties causally affect an audience's attitudes and behaviors. Because text properties are often interlinked (e.g., angry reviews use profane language), we must control for possible latent confounding to isolate causal effects. Recent literature proposes adapting large language models (LLMs) to learn latent representations of text that successfully predict both treatment and the outcome. However, because the treatment is a component of the text, these deep learning methods risk learning representations that actually encode the treatment itself, inducing overlap bias. Rather than depending on post-hoc adjustments, we introduce a new experimental design that handles latent confounding, avoids the overlap issue, and unbiasedly estimates treatment effects. We apply this design in an experiment evaluating the persuasiveness of expressing humility in political communication. Methodologically, we demonstrate that LLM-based methods perform worse than even simple bag-of-words models using our real text and outcomes from our experiment. Substantively, we isolate the causal effect of expressing humility on the perceived persuasiveness of political statements, offering new insights on communication effects for social media platforms, policy makers, and social scientists.

Manually annotating data for computational social science tasks can be costly, time-consuming, and emotionally draining. While recent work suggests that LLMs can perform such annotation tasks in zero-shot settings, little is known about how prompt design impacts LLMs' compliance and accuracy. We conduct a large-scale multi-prompt experiment to test how model selection (ChatGPT, PaLM2, and Falcon7b) and prompt design features (definition inclusion, output type, explanation, and prompt length) impact the compliance and accuracy of LLM-generated annotations on four CSS tasks (toxicity, sentiment, rumor stance, and news frames). Our results show that LLM compliance and accuracy are highly prompt-dependent. For instance, prompting for numerical scores instead of labels reduces all LLMs' compliance and accuracy. The overall best prompting setup is task-dependent, and minor prompt changes can cause large changes in the distribution of generated labels. By showing that prompt design significantly impacts the quality and distribution of LLM-generated annotations, this work serves as both a warning and practical guide for researchers and practitioners.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. New Mexico's Democrat-led Legislature delivered on a handful of the governor's major priorities in her calls for public safety reforms, gun control, housing construction and the use of incentives to forge new solutions to climate change as lawmakers adjourned their 30-day annual session Thursday. Lujan Grisham praised a trio of public safety bills that ban some guns at voting locations, extend a waiting period on gun purchases to seven days and give judges an extra opportunity to deny bail to defendants who are charged with new crimes while already awaiting trial on a felony. But she also delivered a grim assessment of violent crime across the state -- invoking the stabbing death last week of a Las Cruces patrol officer at the hands of a man with a record of crime and mental illness.

Families of gun violence victims are using artificial intelligence to recreate their loved ones' voices and taunt lawmakers who oppose gun control on the sixth anniversary of the Parkland massacre. The robocall messages are being sent to senators and House members who support the National Rifle Association and Second Amendment rights in a campaign that launched on Valentine's Day, Wednesday, according to the Associated Press. Manuel and Patricia Oliver, whose son Joaquin "Guac" Oliver died in the 2018 high school shooting in Parkland, Florida, said the campaign run through The Shotline website is intended to spur Congress to ban the sale of guns like the AR-15 rifle. "We come from a place where gun violence is a problem, but you will never see a 19-year-old with an AR-15 getting into a school and shooting people," Manuel Oliver told the Associated Press in an interview. The Olivers, immigrants from Venezuela, became activists after Joaquin and 13 other students at Marjory Stoneman Douglas High School were murdered by a 19-year-old killer with a rifle.

This paper presents an overview of the ImageArg shared task, the first multimodal Argument Mining shared task co-located with the 10th Workshop on Argument Mining at EMNLP 2023. The shared task comprises two classification subtasks - (1) Subtask-A: Argument Stance Classification; (2) Subtask-B: Image Persuasiveness Classification. The former determines the stance of a tweet containing an image and a piece of text toward a controversial topic (e.g., gun control and abortion). The latter determines whether the image makes the tweet text more persuasive. The shared task received 31 submissions for Subtask-A and 21 submissions for Subtask-B from 9 different teams across 6 countries. The top submission in Subtask-A achieved an F1-score of 0.8647 while the best submission in Subtask-B achieved an F1-score of 0.5561.

Recent developments in natural language processing have demonstrated the potential of large language models (LLMs) to improve a range of educational and learning outcomes. Of recent chatbots based on LLMs, ChatGPT and Bard have made it clear that artificial intelligence (AI) technology will have significant implications on the way we obtain and search for information. However, these tools sometimes produce text that is convincing, but often incorrect, known as hallucinations. As such, their use can distort scientific facts and spread misinformation. To counter polarizing responses on these tools, it is critical to provide an overview of such responses so stakeholders can determine which topics tend to produce more contentious responses -- key to developing targeted regulatory policy and interventions. In addition, there currently exists no annotated dataset of ChatGPT and Bard responses around possibly polarizing topics, central to the above aims. We address the indicated issues through the following contribution: Focusing on highly polarizing topics in the US, we created and described a dataset of ChatGPT and Bard responses. Broadly, our results indicated a left-leaning bias for both ChatGPT and Bard, with Bard more likely to provide responses around polarizing topics. Bard seemed to have fewer guardrails around controversial topics, and appeared more willing to provide comprehensive, and somewhat human-like responses. Bard may thus be more likely abused by malicious actors. Stakeholders may utilize our findings to mitigate misinformative and/or polarizing responses from LLMs

Another month, another flood of weird, wonderful and cute images generated by an artificial intelligence. In April, OpenAI showed off its new picture-making neural network, DALL-E 2, which could produce remarkable high-res images of almost anything it was asked to. Now, just a few weeks later, Google Brain has revealed its own image-making AI, called Imagen. And it performs even better than DALL-E 2: it scores higher on a standard measure for rating the quality of computer-generated images and the pictures it produced were preferred by a group of human judges. But like OpenAI did with DALL-E, Google is going all in on cuteness.

In this paper we suggest a minimally-supervised approach for identifying nuanced frames in news article coverage of politically divisive topics. We suggest to break the broad policy frames suggested by Boydstun et al., 2014 into fine-grained subframes which can capture differences in political ideology in a better way. We evaluate the suggested subframes and their embedding, learned using minimal supervision, over three topics, namely, immigration, gun-control and abortion. We demonstrate the ability of the subframes to capture ideological differences and analyze political discourse in news media.

Scientific studies do not find any links between video games and gun violence. The claim that they do has been repeatedly tested, studied and debunked. Yet on Monday, US president Donald Trump insisted that "gruesome and grisly video games" were causative in the gun massacre deaths of 22 people in El Paso and another 9 in Dayton (not Toledo) Ohio. Why scapegoat video games and demonise the people who play them? It's established that science, expertise, evidence and the truth are not dominant themes of the Trump presidency, and with increasing numbers of people bleeding to death in US streets, he has to find someone – something – anything!

JAKARTA, Indonesia – Esports organizers say don't blame the games. Executives at the Asian Games have expressed sympathy for the victims of the deadly shooting at a video game tournament in a Florida shopping mall. But Kenneth Fok, president of the Asian Electronic Sports Federation, said the shooting was more a reflection of U.S. gun laws than the gaming community. U.S. authorities say 24-year-old David Katz of Baltimore killed two people and wounded nine others before fatally shooting himself Sunday at a Madden tournament being held at a riverfront mall in Jacksonville. "Of course tragedies like this should never happen. One is already too many," Fok told a news conference Wednesday about the introduction of esports at the Asian Games.