FeelsGoodMan: Inferring Semantics of Twitch Neologisms
Twitch chats pose a unique problem in natural language understanding due to a large presence of neologisms, specifically emotes. There are a total of 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. Our paper makes a two fold contribution. First we establish a new baseline for sentiment analysis on Twitch data, outperforming the previous supervised benchmark by 7.9% points. Secondly, 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 emote knowledge into sentiment classifiers trained on extraneous datasets such as movie reviews or Twitter.
Code (0)
등록된 구현이 없습니다.
Tasks
Natural Language UnderstandingSentiment AnalysisWord EmbeddingsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FeelsGoodMan: Inferring Semantics of Twitch Neologisms
Twitch chat messages pose a unique problem in natural language understanding due to a large presence of neologisms, specifically emotes. There are a total of 8.06 million emotes, over 400k of which were observed during t…
Natural Language UnderstandingSentiment AnalysisWord EmbeddingsNEO-BENCH: Evaluating Robustness of Large Language Models with Neologisms
The performance of Large Language Models (LLMs) degrades from the temporal drift between data used for model training and newer text seen during inference. One understudied avenue of language change causing data drift is…
Machine TranslationNatural Language UnderstandingSentenceToxiTwitch: Toward Emote-Aware Hybrid Moderation for Live Streaming Platforms
The rapid growth of live-streaming platforms such as Twitch has introduced complex challenges in moderating toxic behavior. Traditional moderation approaches, such as human annotation and keyword-based filtering, have de…
A primer on getting neologisms from foreign languages to under-resourced languages
Mainly due to lack of support, most under-resourced languages have a reduced lexicon in most realms and domains of increasing importance, then their speakers need to significantly augment it. Although neologisms should a…
Common Sense ReasoningUnsupervised Neologism Normalization Using Embedding Space Mapping
This paper presents an approach for detecting and normalizing neologisms in social media content. Neologisms refer to recent expressions that are specific to certain entities or events and are being increasingly used by …
Natural Language UnderstandingText Normalization