Figure - uploaded by Mirko Lenz
Content may be subject to copyright.
Effectiveness results of different prompting strategies with LLMs with the best metrics for each test dataset marked in bold.
Source publication
The increasing usage of social networks has led to a growing number of discussions on the Internet that are a valuable source of argumentation that occurs in real time. Such conversations are often made up of a large number of participants and are characterized by a fast pace. Platforms like X/Twitter and Hacker News (HN) allow users to respond to...
Contexts in source publication
Context 1
... remaining hypotheses can be tested with the results presented in Table 3, starting with the impact of adding context information to the prompts (H2). First, we check whether the contextualized prompting strategy is more effective than the isolated one. ...Similar publications
Generative Artificial Intelligence (GenAI) tools, like ChatGPT, have made it easy to create text, music, images, and other types of media. GenAI, a type of AI technology, has rapidly gained fame and popularity for its ability to generate new content. Notably, its applications allow anyone to produce natural conversations and content, making it incr...
Attention to environmental, social, and governance (ESG) investing has grown in recent years. Even after the SARS-CoV-2 (COVID-19) global pandemic, there has been a rise in financial instruments that are structured according to certain prescribed “sustainable finance” objectives. From a risk management perspective, and as we continue to see a rise...
Joint Multimodal Aspect-based Sentiment Analysis (JMASA) is a significant task in the research of multimodal fine-grained sentiment analysis, which combines two subtasks: Multimodal Aspect Term Extraction (MATE) and Multimodal Aspect-oriented Sentiment Classification (MASC). Currently, most existing models for JMASA only perform text and image feat...
Opinion mining refers to computational techniques for analyzing the opinions that are extracted from various data sources. Opinion mining involves computational treatment of opinion and subjectivity in text. Before making any decision it is necessary to analyze what other people think. Customers or other people post their opinion, review, experienc...
1✉ Abstrak Penelitian ini bertujuan untuk menganalisis sentimen pengguna Twitter terhadap kendaraan listrik menggunakan teknik pembelajaran mesin. Data dikumpulkan dari Twitter dengan menggunakan kata kunci terkait kendaraan listrik. Data yang diperoleh diolah melalui beberapa tahap seperti pembersihan data, tokenisasi, dan stemming. Selanjutnya, d...
