SenticNet 3: A Common and Common-Sense Knowledge Base for Cognition-Driven Sentiment Analysis

By Erik Cambria, Daniel J. Olsher, Dheeraj Rajagopal. AAAI Conference on Artificial Intelligence, 2014

450 citations recorded by the source corpus.

SenticNet is a publicly available semantic and affective resource for concept-level sentiment analysis. Rather than using graph-mining and dimensionality-reduction techniques, SenticNet 3 makes use of "energy flows" to connect various parts of extended common and common-sense knowledge representations to one another. SenticNet 3 models nuanced semantics and sentics (that is, the conceptual and affective information associated with multi-word natural language expressions), representing information with a symbolic opacity of an intermediate nature between that of neural networks and typical symbolic systems.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/8a0a8568acf2b95c9cb471e28ee6b25c5e4fe186

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

SenticNet 4: A Semantic Resource for Sentiment Analysis Based on Conceptual Primitives (2016, background): “SenticNet (Cambria et al., 2014) captures such latent information in terms of semantics and sentics , i.e., the denotative and connotative information commonly associated with real-world objects, actions, events, and people.”
Aspect extraction for opinion mining with a deep convolutional neural network (2016, methodology): “In some of our experiments, we used a set of linguistic ) that leverage on SenticNet (Cambria et al., 2014a) and its extensions (Poria et al., 2012b,a), a concept-level knowledge base for sentiment analysis built by means of sentic computing (Cambria and Hussain, 2015).”
A Rule-Based Approach to Aspect Extraction from Product Reviews (2014, methodology): “• if t has any direct object relation with a token n and the POS of the token is Noun and n is not in SenticNet, then n is extracted as an aspect.”
Fusing audio, visual and textual clues for sentiment analysis from multimodal content (2016, background): “Significant studies have been done to identify positive, negative, or neutral sentiment associated with words [30,31], multi-words [32], phrases [33], sentences [34], and documents [35].”
A survey on opinion mining and sentiment analysis: Tasks, approaches and applications (2015, background): “S# Tasks and applications #Articles References 1 Subjectivity Classification 6 [44], [75], [110], [163], [167], [174] 2 Polarity determination 43 [12], [26], [29], [32], [33], [35], [40], [45], [48], [50], [54], [57], [66], [85], [95], [96], [108], [109], [112], [114], [123], [126], [154], [156], [1”
Select-additive learning: Improving generalization in multimodal sentiment analysis (2016, background): “Originating from analysis of the textual modality, sentiment analysis has been carried out at the word level [15], phrase level [16] and sentence level [17].”
Commonsense Reasoning for Natural Language Understanding: A Survey of Benchmarks, Resources, and Approaches (2019, background): “IsaCore may also be a useful resource for commonsense reasoning.”
Sentic patterns: Dependency-based rules for concept-level sentiment analysis (2014, background): “Current approaches to concept-level sentiment analysis mainly leverage on existing affective knowledge bases such as ANEW [3], WordNet-Affect [4], ISEAR [5], SentiWordNet [6], and SenticNet [7].”