We present a novel digital humanities method for representing our Twitch chatters as user embeddings created by a large language model (LLM). We cluster these embeddings automatically using affinity propagation and further narrow this clustering down through manual analysis. We analyze the chat of one stream by each Twitch streamer: SmallAnt, DougDoug and PointCrow. Our findings suggest that each streamer has their own type of chatters, however two categories emerge for all of the streamers: supportive viewers and emoji and reaction senders. Repetitive message spammers is a shared chatter category for two of the streamers.

AI agents powered by Large Language Models (LLMs) have made significant advances, enabling them to assist humans in diverse complex tasks and leading to a revolution in human-AI coordination. LLM-powered agents typically require invoking LLM APIs and employing artificially designed complex prompts, which results in high inference latency. While this paradigm works well in scenarios with minimal interactive demands, such as code generation, it is unsuitable for highly interactive and real-time applications, such as gaming. Traditional gaming AI often employs small models or reactive policies, enabling fast inference but offering limited task completion and interaction abilities. In this work, we consider Overcooked as our testbed where players could communicate with natural language and cooperate to serve orders. We propose a Hierarchical Language Agent (HLA) for human-AI coordination that provides both strong reasoning abilities while keeping real-time execution. In particular, HLA adopts a hierarchical framework and comprises three modules: a proficient LLM, referred to as Slow Mind, for intention reasoning and language interaction, a lightweight LLM, referred to as Fast Mind, for generating macro actions, and a reactive policy, referred to as Executor, for transforming macro actions into atomic actions. Human studies show that HLA outperforms other baseline agents, including slow-mind-only agents and fast-mind-only agents, with stronger cooperation abilities, faster responses, and more consistent language communications.

Teamwork is a necessary competency for students that is often inadequately assessed. Towards providing a formative assessment of student teamwork, an automated natural language processing approach was developed to identify teamwork dimensions of students' online team chat. Developments in the field of natural language processing and artificial intelligence have resulted in advanced deep transfer learning approaches namely the Bidirectional Encoder Representations from Transformers (BERT) model that allow for more in-depth understanding of the context of the text. While traditional machine learning algorithms were used in the previous work for the automatic classification of chat messages into the different teamwork dimensions, our findings have shown that classifiers based on the pre-trained language model BERT provides improved classification performance, as well as much potential for generalizability in the language use of varying team chat contexts and team member demographics. This model will contribute towards an enhanced learning analytics tool for teamwork assessment and feedback.

A few years ago, I managed to receive 1,000 emails between boarding a plane in San Francisco and landing in New Orleans five hours later. Maybe 40 of those 1,000 were emails that I needed to respond to, but given the overwhelming volume in my inbox, a lot of them ended up going unanswered. Filters help organize things a bit, but now a new email app is bringing in the big guns to tackle the problem: artificial intelligence. Called Astro, the app essentially offers many of the same features as previous aspiring inbox-zero apps. You can snooze messages you see so they surface at your convenience, mute particular senders, and set a priority inbox that surfaces those emails from VIP senders that otherwise might end up buried amid Bed Bath & Beyond coupons.

As expected, Zoom is looking to take on the likes of Microsoft 365 and Google Workspace in more areas than group video calls and chats. At its Zoomtopia conference, the company announced a bunch of features that are coming to its platform, including two key ones for productivity: email and calendars. You can connect third-party email and calendar services to Zoom and access them through the desktop app. The company says that can help save you time instead of having to switch between apps and perhaps needing to hunt for the right tab in your browser. Those on the Zoom One Pro or Zoom Standard Pro plans will be able to set up email accounts through the platform, and folks with certain plans have the option to use custom domains.

Suppose your social network for chinchilla owners has taken off. Your flagship app contains an embedded chat client where community members discuss chinchilla-related topics in real-time. As your user base grows, so does its value as a target for advertising. You now have a spam problem on your hands, and your small team of engineers has only so much time they can dedicate to this arms race. Here's how Wallaroo can help.

Called Astro, the app essentially offers many of the same features as previous aspiring inbox-zero apps. You can snooze messages you see so they surface at your convenience, mute particular senders, and set a priority inbox that surfaces those emails from VIP senders that otherwise might end up buried amid Bed Bath & Beyond coupons. What makes Astro different is how it creates that priority inbox. Just like other programs, you can designate people you'd like to prioritize. Astro takes care of that automatically by putting a few people in there based on whom you're chatting with on a regular basis.

During my time at betaworks last summer, I worked on extracting principal topics from messages that Digg's Facebook Messenger Bot received. This post explains a topic extraction method I created specifically for chat messages, which we later used to develop RIO -- a topic mining engine that uses reinforcement to tune its algorithm and automatically predict tags for chat messages and news articles. Conversational bots today understand user messages only when rules are hard-coded to match the exact message pattern. Such scripted bots find it hard to scale and can be frustrating for users who want to have a basic natural language exchange with the bot. Every bot provides a service (for Digg this is news), but users don't necessarily restrict their messages to that.

Analyzing chat traffic has important applications for both the military and the civilian world. This paper presents a case study of a real-world application of chat analysis in support of team training exercise in the military. It compares the results of an unsupervised learning approach with those of a supervised classification approach. The paper also discusses some of the specific challenges presented by this domain.

Analyzing chat traffic has important applications for both the military and the civilian world. This poster will report on an effort to automatically separate chat messages into topic threads.