Sentiment Analysis
Sentiment analysis aims to automatically determine the emotional tone expressed in text, aiming to understand opinions and attitudes. Current research heavily focuses on leveraging large language models (LLMs) like BERT and its variants, along with other architectures such as graph neural networks, to improve accuracy and efficiency, particularly in multimodal settings and low-resource languages. This field is crucial for various applications, including market research, social media monitoring, and understanding public opinion, driving advancements in natural language processing and impacting decision-making across numerous sectors.
Papers
NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysis
Mingyang Wang, Heike Adel, Lukas Lange, Jannik Strötgen, Hinrich Schütze
HausaNLP at SemEval-2023 Task 10: Transfer Learning, Synthetic Data and Side-Information for Multi-Level Sexism Classification
Saminu Mohammad Aliyu, Idris Abdulmumin, Shamsuddeen Hassan Muhammad, Ibrahim Said Ahmad, Saheed Abdullahi Salahudeen, Aliyu Yusuf, Falalu Ibrahim Lawan
The Emotions of the Crowd: Learning Image Sentiment from Tweets via Cross-modal Distillation
Alessio Serra, Fabio Carrara, Maurizio Tesconi, Fabrizio Falchi
SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)
Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Seid Muhie Yimam, David Ifeoluwa Adelani, Ibrahim Sa'id Ahmad, Nedjma Ousidhoum, Abinew Ayele, Saif M. Mohammad, Meriem Beloucif, Sebastian Ruder
Masakhane-Afrisenti at SemEval-2023 Task 12: Sentiment Analysis using Afro-centric Language Models and Adapters for Low-resource African Languages
Israel Abebe Azime, Sana Sabah Al-Azzawi, Atnafu Lambebo Tonja, Iyanuoluwa Shode, Jesujoba Alabi, Ayodele Awokoya, Mardiyyah Oduwole, Tosin Adewumi, Samuel Fanijo, Oyinkansola Awosan, Oreen Yousuf