“We first review previous research on using social networks to help recommend items to users. A crucial component of SPF is that it infers the influence that users have with each other. In previous wo…
“…there is currently a lack of systematic research on the behavioral characteristics of LLMs-driven social bots and their impact on social networks. We have curated data from Chirper, a Twitter-like s…
Attention has a practical and specific online context. It has to do with managing the flood of data and advertisements vying for your time, which is finite. The metadata 'exhaust' (feeds, clicks, link…
As more social interaction takes place online, researchers have become interested in studying the discourse occurring in online social media. From these studies, researchers can examine how people con…
Unfortunately, the chosen weights can often lead to unintended consequences. For example, when Facebook introduced emoji reactions, they gave all emoji reactions a weight five times that of the standa…
One of the main challenges online social systems face is the prevalence of antisocial behavior, such as harassment and personal attacks. In this work, we introduce the task of predicting from the very…
“Conspiracy theories are a paradigmatic example of beliefs that, once adopted, are extremely difficult to dispel. Influential psychological theories propose that conspiracy beliefs are uniquely resist…
In this study, we wish to showcase the unique utility of large language models (LLMs) in financial semantic annotation and alpha signal discovery. Leveraging a corpus of company-related tweets, we use…
method leverages the inherent vulnerabilities of LLMs in handling world knowledge, which can be exploited by attackers to unconsciously spread fabricated information. Through extensive experiments, we…
In this paper, we propose a method to forecast the arrival of hostile comments on Instagram posts. In order to support different intervention strategies, as well as to assess the difficulty of variant…
While a few methods improve content, they solely transfer the style of texts to be more formal (Rao and Tetreault, 2018; Lai et al., 2021), less subjective (Pryzant et al., 2020; Liu et al., 2021a), o…
we test whether GPT-3.5 and GPT-4 can derive the Big Five personality traits from users’ Facebook status updates in a zero-shot learning scenario. Our results show an average correlation of r = .29 (r…
We categorize LLM applications for social networks into three categories. First is knowledge tasks where users want to find new knowledge and information, such as search and question-answering. Second…
To the human eye, AI-generated outputs of large language models have increasingly become indistinguishable from human-generated outputs. Therefore, to determine the linguistic properties that separate…
Existing theories and research in human-machine communication (HMC) suggest that humans tend to mindlessly anthropomorphize the media technologies they interact with, that is, to attribute humans’ men…
Online discussion moderators must make adhoc decisions about whether the contributions of discussion participants are appropriate or should be removed to maintain civility. Existing research on offens…
We address this gap by analyzing data from the AI Search Arena, a head-to-head evaluation platform for AI search systems. The dataset comprises over 24,000 conversations and 65,000 responses from mode…
This report outlines several case studies on how actors have misused our models, as well as the steps we have taken to detect and counter such misuse. By sharing these insights, we hope to protect the…
“It is proposed that posters will be influenced by another’s opinion only when it is negative. Negative evaluators are seen as more intelligent, competent, and expert than positive evaluators (Amabile…
Multiple studies on content moderation have identified a problem of scale: even if antisocial behavior is a small fraction of all content that gets posted, the sheer size of modern online platforms, t…
we present Proxona, a system for defining and extracting representative audience personas from the comments. Creators converse with personas to gain insights into their preferences and engagement, sol…
“We represent a topic of discussion with a conversation graph. In such a graph, vertices represent users, and edges represent conversation activity and interactions, such as posts, comments, mentions,…
This paper introduces RLNVR (Reinforcement Learning from Non-Verified Rewards), a framework for training language models using noisy, real-world feedback signals without requiring explicit human verif…
To improve the reading experience, many news sites organize news into topical collections, called stories. In this work, we present an approach for implementing real-time story identification for a ne…
“Traditional recommender systems always ignore social relationships among users. But in our real life, when we are asking our friends for recommendations of nice digital cameras or touching movies, we…
“Social media (SM) plays an increasingly important role in our lives. As of 2021, seven out of ten US adults use at least one social media platform like Facebook, Twitter, Instagram, or Pinterest [3].…
Models of how things spread often assume that transmission mechanisms are fixed over time. However, social contagions–the spread of ideas, beliefs, innovations–can lose or gain in momentum as they spr…
The implementation of prompting strategies represents a significant departure from traditional NLP model training methods. By employing these strategies, LLMs can generate predictions without the exte…
Synthetic data generation with Large Language Models (LLMs) has emerged as a promising paradigm for augmenting natural data over a nearly infinite range of tasks. However, most existing methods are fa…
Recent technological advancements, involving generative AI and personality inference from consumed text, can potentially create a highly scalable “manipulation machine” that targets individuals based …
The widespread use of social media has led to a surge in popularity for automated methods of analyzing public opinion. Supervised methods are adept at text categorization, yet the dynamic nature of so…
Recent advancements, however, have equipped LLMs with web-browsing capabilities, enabling real-time information retrieval and multi-step reasoning over live web content. While prior studies have demon…