SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining

By Stefano Baccianella, Andrea Esuli, Fabrizio Sebastiani. 2010

3,472 citations recorded by the source corpus.

In this work we present SENTIWORDNET 3.0, a lexical resource explicitly devised for supporting sentiment classification and opinion mining applications. SENTIWORDNET 3.0 is an improved version of SENTIWORDNET 1.0, a lexical resource publicly available for research purposes, now currently licensed to more than 300 research groups and used in a variety of research projects worldwide. Both SENTIWORDNET 1.0 and 3.0 are the result of automatically annotating all WORDNET synsets according to their degrees of positivity, negativity, and neutrality. SENTIWORDNET 1.0 and 3.0 differ (a) in the versions of WORDNET which they annotate (WORDNET 2.0 and 3.0, respectively), (b) in the algorithm used for automatically annotating WORDNET, which now includes (additionally to the previous semi-supervised learning step) a random-walk step for refining the scores. We here discuss SENTIWORDNET 3.0, especially focussing on the improvements concerning aspect (b) that it embodies with respect to version 1.0. We also report the results of evaluating SENTIWORDNET 3.0 against a fragment of WORDNET 3.0 manually annotated for positivity, negativity, and neutrality; these results indicate accuracy improvements of about 20% with respect to SENTIWORDNET 1.0.

Subfields: Artificial Intelligence, Natural Language Processing, Evaluation & Benchmarks

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

In Natural Language Processing

In Evaluation & Benchmarks

Citations in the corpus

Language Models are Few-Shot Learners (2020, methodology): “We measured sentiment using Senti WordNet [BES10] for the words which co-occurred disproportionately with each race.”
Hafez: an Interactive Poetry Generation System (2017, methodology): “We pre-build a word list together with its sentiment scores based on Senti-WordNet (Baccianella et al., 2010). f ( w ) equals to w 0 s sentiment score.”
Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models (2022, background): “Sentiment classiﬁers vary; Huang et al. [54] use the Google Cloud Sentiment API, 10 whereas Brown et al. [21] use SentiWordNet [7].”
When does a compliment become sexist? Analysis and classification of ambivalent sexism using twitter data (2017, methodology): “We calculated the positive score and the negative score for each phrase in the tweet, us-ing SentiWordNet (Baccianella et al., 2010) and subjectivity lexicon (Taboada et al., 2011).”
DynaSent: A Dynamic Benchmark for Sentiment Analysis (2020, background): “Other important examples are Opin-ionFinder (Wilson et al., 2005), LIWC (Pennebaker et al., 2007), MPQA, Opinion Lexicon (Liu, 2011), SentiWordNet (Baccianella et al., 2010), and the valence and arousal ratings of Warriner et al. (2013).”
Use of Sentiment Analysis for Capturing Patient Experience From Free-Text Comments Posted Online (2013, methodology): “It would also be useful to compare the relatively simple techniques used in this analysis against other platforms and tools used for the sentiment analysis and opinion mining process, for example WordNet Affect [29] and SentiWordNet [30,31].”
Stock Prediction Using Twitter Sentiment Analysis (2011, methodology): “We tried several standard tools like OpinionFinder, SentiWordnet [5] etc. for our problem but found them inadequate and/or ineﬃcient and therefore decided to develop our own analysis code.”
Generating Fluent Adversarial Examples for Natural Languages (2019, positive): ““not”) in IMDB experiments with SentiWordNet (Esuli and Sebastiani, 2006; Baccianella et al., 2010).”
Improving the Interpretability of Neural Sentiment Classifiers via Data Augmentation (2019, methodology): “In this work, we use the words listed in the SentiWordNet corpus (Baccianella et al., 2010) and their sentiment polarity scores.”
Building Large-Scale Twitter-Specific Sentiment Lexicon : A Representation Learning Approach (2014, methodology): “Then, graph propagation algorithms, such as pagerank (Esuli and Sebastiani, 2007), label propagation (Rao and Ravichandran, 2009) or random walk (Baccianella et al., 2010), are utilized to iteratively calculate the sentiment score of each item.”
SenticNet 6: Ensemble Application of Symbolic and Subsymbolic AI for Sentiment Analysis (2020, methodology): “The former school of thought focuses on the construction of knowledge bases for the identification of polarity in text, e.g., WordNet-Affect [55], SentiWordNet [3], and SenticNet [10].”
Large Scale Sentiment Learning with Limited Labels (2017, background): “SentiWordNet [2] is a dictionary of words and their associated sentiment.”
Sentiment Analysis of Short Informal Texts (2014, neutral): “…(NRC Emotion Lexicon, Bing Liu’s Lexicon, and MPQA Subjectivity Lexicon), (2) automatically created, general-purpose lexicons (SentiWordNet 3.0 (Baccianella, Esuli, & Sebastiani, 2010), MSOL (Mohammad et al., 2009), and Osgood Evaluative Factor Ratings (Turney & Littman, 2003)), and (3) our…”
Sentiment analysis using deep learning architectures: a review (2019, background): “(2017b), Baktha and Tripathy (2017), Poria et al. (2017b) and Wang et al. (2018a). • Capsule networks CNN architecture suffers from certain limitations.”
Comparison and Modelling of Country-level Microblog User and Activity in Cyber-physical-social Systems Using Weibo and Twitter Data (2019, methodology): “The English and Chinese microblog messages were analysed by SentiWordNet English sentiment dictionary and NTUSD Chinese Emotion Dictionary.”
Sentiment strength detection for the social web (2012, background): “, 1966), the ANEW words (Bradley & Lang, 1999), SentiWordNet (Baccianella et al., 2010) WordNet Affect (Strapparava & Valitutti, 2004) or the LIWC dictionary (Pennebaker et al.”