Analyzing Pokémon and Mario Streamers' Twitch Chat with LLM-based User Embeddings

• URL: http://arxiv.org/abs/2411.10934v1
• Date: Sun, 17 Nov 2024 02:08:03 GMT
• Title: Analyzing Pokémon and Mario Streamers' Twitch Chat with LLM-based User Embeddings
• Authors: Mika Hämäläinen, Jack Rueter, Khalid Alnajjar,
• Abstract summary: 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.
• Score: 1.788784870849724
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Virtual Stars, Real Fans: Understanding the VTuber Ecosystem [8.461062537658846]
  We conduct a comprehensive analysis of VTuber viewers on Bilibili, a leading livestreaming platform where nearly all VTubers in China stream. By compiling a first-of-its-kind dataset covering 2.7M livestreaming sessions, we investigate the characteristics, engagement patterns, and influence of VTuber viewers. We leverage to develop a tool to "recommend" future subscribers to VTubers.
  arXiv  Detail & Related papers  (2025-02-03T17:33:54Z)
• Progressive Pruning: Estimating Anonymity of Stream-Based Communication [1.8434042562191815]
  We introduce Progressive Pruning, a methodology suitable for estimating the anonymity level of streams. By mimicking an intersection attack, it captures the susceptibility of streams against traffic analysis attacks. We apply it to simulations of tailored examples of stream communication as well as to large-scale simulations of Tor using our novel TorFS simulator.
  arXiv  Detail & Related papers  (2024-10-11T10:40:51Z)
• Game Development as Human-LLM Interaction [55.03293214439741]
  This paper introduces the Chat Game Engine (ChatGE) powered by Human-LLM interaction. ChatGE allows everyone to develop a custom game using natural language through Human-LLM interaction. We construct a ChatGE for poker games as a case study and evaluate it from two perspectives: interaction quality and code correctness.
  arXiv  Detail & Related papers  (2024-08-18T07:06:57Z)
• WildChat: 1M ChatGPT Interaction Logs in the Wild [88.05964311416717]
  WildChat is a corpus of 1 million user-ChatGPT conversations, which consists of over 2.5 million interaction turns. In addition to timestamped chat transcripts, we enrich the dataset with demographic data, including state, country, and hashed IP addresses.
  arXiv  Detail & Related papers  (2024-05-02T17:00:02Z)
• CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations [97.75037148056367]
  CoVoMix is a novel model for zero-shot, human-like, multi-speaker, multi-round dialogue speech generation. We devise a comprehensive set of metrics for measuring the effectiveness of dialogue modeling and generation.
  arXiv  Detail & Related papers  (2024-04-10T02:32:58Z)
• ChatAnything: Facetime Chat with LLM-Enhanced Personas [87.76804680223003]
  We propose the mixture of voices (MoV) and the mixture of diffusers (MoD) for diverse voice and appearance generation. For MoV, we utilize the text-to-speech (TTS) algorithms with a variety of pre-defined tones. MoD, we combine the recent popular text-to-image generation techniques and talking head algorithms to streamline the process of generating talking objects.
  arXiv  Detail & Related papers  (2023-11-12T08:29:41Z)
• Analyzing Norm Violations in Live-Stream Chat [49.120561596550395]
  We study the first NLP study dedicated to detecting norm violations in conversations on live-streaming platforms. We define norm violation categories in live-stream chats and annotate 4,583 moderated comments from Twitch. Our results show that appropriate contextual information can boost moderation performance by 35%.
  arXiv  Detail & Related papers  (2023-05-18T05:58:27Z)
• Uncovering the Dark Side of Telegram: Fakes, Clones, Scams, and Conspiracy Movements [67.39353554498636]
  We perform a large-scale analysis of Telegram by collecting 35,382 different channels and over 130,000,000 messages. We find some of the infamous activities also present on privacy-preserving services of the Dark Web, such as carding. We propose a machine learning model that is able to identify fake channels with an accuracy of 86%.
  arXiv  Detail & Related papers  (2021-11-26T14:53:31Z)
• A study on Channel Popularity in Twitch [0.0]
  There have been few studies about the prediction of streamers' popularity on Twitch. Streamer data was collected through consistent tracking using Twitch's API during a 4 weeks period. From the results, we found that the frequency of streaming sessions, the types of content and the length of the streams are major factors in determining how much viewers and subscribers streamers can gain during sessions.
  arXiv  Detail & Related papers  (2021-11-10T20:55:20Z)
• FeelsGoodMan: Inferring Semantics of Twitch Neologisms [0.7734726150561088]
  There are 8.06 million emotes, over 400k of which were used in the week studied. There is virtually no information on the meaning or sentiment of emotes, and with a constant influx of new emotes and drift in their frequencies, it becomes impossible to maintain an updated manually-labeled dataset. We introduce a simple but powerful unsupervised framework based on word embeddings and k-NN to enrich existing models with out-of-vocabulary knowledge. This framework allows us to auto-generate a pseudo-dictionary of emotes and we show that we can nearly match the supervised benchmark above even when injecting such
  arXiv  Detail & Related papers  (2021-08-18T23:46:46Z)
• Moment-to-moment Engagement Prediction through the Eyes of the Observer: PUBG Streaming on Twitch [0.9281671380673304]
  We build prediction models for viewers' engagement based on data collected from the popular battle royale game PlayerUnknown's Battlegrounds. In particular, we collect viewers' chat logs and in-game telemetry data from several hundred matches of five popular streamers. Our key findings showcase that engagement models trained solely on 40 gameplay features can reach accuracies of up to 80% on average and 84% at best.
  arXiv  Detail & Related papers  (2020-08-17T10:40:34Z)
• I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents [69.68400056148336]
  We train a goal-oriented model with reinforcement learning against an imitation-learned chit-chat'' model. We show that both models outperform an inverse model baseline and can converse naturally with their dialogue partner in order to achieve goals.
  arXiv  Detail & Related papers  (2020-02-07T16:22:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.