Paper Type
Complete
Paper Number
PACIS2025-1276
Description
Memes convey sentiments and humor, and are useful to stimulate interactions and engagements of audiences during livestreaming. However, little research aids streamers in showing appropriate memes in livestreaming environments. Suggesting relevant memes timely in a livestream poses significant challenges as it requires multimodal cues and a nuanced understanding of the livestream context. This study proposes StreaMeme (liveStream Meme category recommender), a novel system that recommends meme categories for streamers during livestreaming. StreaMeme employs a visual language model (VLM) to analyze memes' humor and sentiments, and digests livestreaming contexts with a large language model (LLM) to reason for meme recommendations. An LLM is fine-tuned to exploit streamer speeches, audience messages, meme explanations, and recommendation reasons; its output is then used for our meme category recommendation. Experimental results on real-world livestreams show that StreaMeme outperforms several baseline methods, including direct LLM prompting and fine-tuned language models in terms of the F0.5 scores.
Recommended Citation
Chen, Pei-Chu; You, Chia-Min; Chen, Ting-Yu; and Chen, Chien Chin, "StreaMeme: Meme Category Recommendation of Livestreaming Using LLMs" (2025). PACIS 2025 Proceedings. 9.
https://aisel.aisnet.org/pacis2025/aiandml/aiandml/9
StreaMeme: Meme Category Recommendation of Livestreaming Using LLMs
Memes convey sentiments and humor, and are useful to stimulate interactions and engagements of audiences during livestreaming. However, little research aids streamers in showing appropriate memes in livestreaming environments. Suggesting relevant memes timely in a livestream poses significant challenges as it requires multimodal cues and a nuanced understanding of the livestream context. This study proposes StreaMeme (liveStream Meme category recommender), a novel system that recommends meme categories for streamers during livestreaming. StreaMeme employs a visual language model (VLM) to analyze memes' humor and sentiments, and digests livestreaming contexts with a large language model (LLM) to reason for meme recommendations. An LLM is fine-tuned to exploit streamer speeches, audience messages, meme explanations, and recommendation reasons; its output is then used for our meme category recommendation. Experimental results on real-world livestreams show that StreaMeme outperforms several baseline methods, including direct LLM prompting and fine-tuned language models in terms of the F0.5 scores.
Comments
AI ML