Skip to search formSkip to main contentSkip to account menu

1 Emote-Controlled Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch . tv Channels

Emote-Controlled

This work explores the possibility of deriving feedback for video streams on Twitch.tv by analyzing the sentiment of live text comments made by stream viewers in highly active channels, and proposes two unsupervised lexicon-based approaches that make heavy use of the information encoded in emotes, as well as a weakly supervised neural network–based classifier trained on the lexicons-based outputs.
View on ACM (opens in a new tab)

Density-based weighting for imbalanced regression

DenseLoss significantly improves model performance for rare data points through its density-based weighting scheme, and is compared to the state-of-the-art method SMOGN, finding that this method mostly yields better performance.
View on Springer (opens in a new tab)

SimLoss: Class Similarities in Cross Entropy

SimLoss is introduced, a drop-in replacement for CCE that incorporates class similarities along with two techniques to construct such matrices from task-specific knowledge that allows for explicit modeling of background knowledge by simply exchanging the loss function, while keeping the neural network architecture the same.
View PDF on arXiv (opens in a new tab)

NICER: Aesthetic Image Enhancement with Humans in the Loop

This work proposes the Neural Image Correction & Enhancement Routine (NICER), a neural network based approach to no-reference image enhancement in a fully-, semi-automatic or fully manual process that is interactive and user-centered and shows that NICER can improve image aesthetics without user interaction.
View PDF on arXiv (opens in a new tab)

Where to Submit? Helping Researchers to Choose the Right Venue

This work introduces WTS, an open and interpretable NLP system that recommends conferences and journals to researchers based on the title, abstract, and/or keywords of a given paper.
View on ACL (opens in a new tab)

Towards Predicting the Subscription Status of Twitch.tv Users - ECML-PKDD ChAT Discovery Challenge 2020

It is investigated whether the subscription status of active users of Twitch can be inferred from their activity patterns in the chats of streamers, and interaction behavior plays a crucial role in solving this task.
View Paper (opens in a new tab)

WueDevils at SemEval-2022 Task 8: Multilingual News Article Similarity via Pair-Wise Sentence Similarity Matrices

We present a system that creates pair-wise cosine and arccosine sentence similarity matrices using multilingual sentence embeddings obtained from pre-trained SBERT and Universal Sentence Encoder…
View on ACL (opens in a new tab)

Anomaly Detection in Beehives using Deep Recurrent Autoencoders

An autoencoder, a deep learning model, which detects any type of anomaly in data independent of its origin, which is able to reveal the same swarms as a simple rule-based swarm detection algorithm but is also triggered by any other anomaly.
View PDF on arXiv (opens in a new tab)

OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning

View via Publisher (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)