• Publications
  • Influence
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
TLDR
We present here a new version of the linked open data resource ConceptNet that is particularly well suited to be used with modern NLP techniques such as word embeddings. Expand
  • 655
  • 158
  • PDF
Representing General Relational Knowledge in ConceptNet 5
TLDR
ConceptNet is a knowledge representation project, providing a large semantic graph that describes general human knowledge and how it is expressed in natural language. Expand
  • 386
  • 78
  • PDF
ConceptNet 3 : a Flexible , Multilingual Semantic Network for Common Sense Knowledge
TLDR
We present ConceptNet 3, which improves the acquisition of new knowledge in ConceptNet and facilitates turning edges of the network back into natural language. Expand
  • 281
  • 46
  • PDF
New Avenues in Opinion Mining and Sentiment Analysis
TLDR
The Web holds valuable, vast, and unstructured information about public opinion. Expand
  • 865
  • 36
  • PDF
ConceptNet 5: A Large Semantic Network for Relational Knowledge
TLDR
ConceptNet is a knowledge representation project, providing a large semantic graph that describes general human knowledge and how it is expressed in natural language. Expand
  • 188
  • 34
  • PDF
SenticNet: A Publicly Available Semantic Resource for Opinion Mining
TLDR
We developed SenticNet, a publicly available semantic resource for opinion mining built using common sense reasoning techniques together with an emotion categorization model and an ontology. Expand
  • 230
  • 21
  • PDF
AnalogySpace: Reducing the Dimensionality of Common Sense Knowledge
TLDR
We are interested in the problem of reasoning over very large common sense knowledge bases. Expand
  • 191
  • 17
  • PDF
SenticNet 2: A Semantic and Affective Resource for Opinion Mining and Sentiment Analysis
TLDR
We developed SenticNet 2, a publicly available semantic and affective resource for opinion mining and sentiment analysis for the development of affect-sensitive applications in fields such as social data mining. Expand
  • 183
  • 12
  • PDF
Digital Intuition: Applying Common Sense Using Dimensionality Reduction
TLDR
We use singular value decomposition to aid in the integration of systems or representations, enabling commonsense reasoning over a broader domain. Expand
  • 88
  • 8
  • PDF
Sentic Computing for social media marketing
TLDR
In a world in which millions of people express their opinions about commercial products in blogs, wikis, fora, chats and social networks, the distillation of knowledge from this huge amount of unstructured information can be a key factor for marketers who want to create an image or identity. Expand
  • 95
  • 5
  • PDF