SenticNet 4: A Semantic Resource for Sentiment Analysis Based on Conceptual Primitives

By Erik Cambria, Soujanya Poria, Rajiv Bajpai, Björn Schuller. International Conference on Computational Linguistics, 2016

313 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/ae32e911a080eeeb3ac08e483f99e3daa649065f

How researchers see this paper

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

Citations in the corpus

SenticNet 5: Discovering Conceptual Primitives for Sentiment Analysis by Means of Context Embeddings (2018, methodology): “2http://sentic.net/downloads 3http://sentic.net/api SenticNet 5 vs. SenticNet 4 We compared the performance of SenticNet 5 with its predecessor SenticNet 4 (Cambria et al. 2016) for the task of sentence-level polarity detection, using sentic patterns.”
Natural language based financial forecasting: a survey (2017, background): “For instance, SenticNet stores four-dimensional values of the hourglass model [17], which is derived from Plutchik’s wheel of emotions model.”
Augmenting End-to-End Dialogue Systems With Commonsense Knowledge (2018, background): “Lastly, we plan to integrate affective knowledge from SenticNet in the dialogue system in order to enhance its emotional intelligence and, hence, achieve a more human-like interaction.”
Bayesian network based extreme learning machine for subjectivity detection (2017, background): “Eventually, the top 50 clue words with highest occurrences in the subjective sentences were considered [42].”
A Practical Guide to Sentiment Analysis (2017, background): “Several commercial and academic tools, e.g., IBM,1 SAS,2 Oracle,3 SenticNet4 and Luminoso,5 track public viewpoints on a large-scale by offering graphical summarizations of trends and opinions in the blogosphere.”
Tensor Fusion Network for Multimodal Sentiment Analysis (2017, methodology): “Various approaches have been proposed to model sentiment from language, including methods that focus on opinionated words (Hu and Liu, 2004; Taboada et al., 2011; Poria et al., 2014b; Cambria et al., 2016), n-grams and language models (Yang and Cardie, 2012), sentiment compositionality and dependenc”
Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence (2019, background): “• SenticLSTM (Ma et al., 2018): an upgraded version of the LSTM+TA+SA model which introduces external information from Sentic-Net (Cambria et al., 2016).”
Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2021, unknown): “ticNet is a publicly available resource for opinion mining and sentiment analysis, which uses dimensionality reduction to infer the polarity of commonsense concepts and provide an affective value for each concept [42, 43, 44, 45, 46, 47].”
SemEval-2018 Task 3: Irony Detection in English Tweets (2018, background): “Among the most frequently used features are lexical features (e.g. n -grams, punctuation and hashtag counts, emoji presence) and sentiment-or emotion-lexicon features (e.g. based on Sen-ticNet (Cambria et al., 2016), VADER (Hutto and Gilbert, 2014), aFinn (Nielsen, 2011)).”
Radical-Based Hierarchical Embeddings for Chinese Sentiment Analysis at Sentence Level (2017, methodology): “Then, we train a sentiment-speciﬁc radical embedding and integrate it with the R semantic to form a radical embedding termed R sentic , which encodes both semantic and sentiment information (Cambria et al. 2016; Poria et al. 2016).”
Context-Dependent Sentiment Analysis in User-Generated Videos (2017, methodology): “While the use of knowledge bases was initially more popular for the identiﬁcation of polarity in text (Cambria et al., 2016; Poria et al., 2016c), sentiment analysis researchers have recently been using statistics-based approaches, with a special focus on supervised statistical meth-ods (Socher et…”
Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM (2018, methodology): “In particular, we use SenticNet (Cambria et al. 2016), a commonsense knowledge base that contains 50,000 concepts associated with a rich set of affective properties (Table 1).”
A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks (2016, methodology): “Since (Joshi et al., 2015) did not mention about the sentiment lexicon they use in the experiment, we used SenticNet (Cambria et al., 2016) in the re-implementation of their method.”
Deep Learning--based Text Classification (2020, methodology): “Although this idea has been investigated for sentiment classification [221], much more research is required to explore how to effectively model and use commonsense knowledge in neural models.”