Build Emotion Lexicon from the Mood of Crowd via Topic-Assisted Joint Non-negative Matrix Factorization

  title={Build Emotion Lexicon from the Mood of Crowd via Topic-Assisted Joint Non-negative Matrix Factorization},
  author={Kaisong Song and Wei Gao and Ling Chen and Shi Feng and Daling Wang and Chengqi Zhang},
  journal={Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval},
  • Kaisong Song, Wei Gao, Chengqi Zhang
  • Published 7 July 2016
  • Computer Science
  • Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval
In the research of building emotion lexicons, we witness the exploitation of crowd-sourced affective annotation given by readers of online news articles. Such approach ignores the relationship between topics and emotion expressions which are often closely correlated. We build an emotion lexicon by developing a novel joint non-negative matrix factorization model which not only incorporates crowd-annotated emotion labels of articles but also generates the lexicon using the topic-specific matrices… 

Figures and Tables from this paper

Dependency-Aware Attention Model for Emotion Analysis for Online News
This paper comes up with an emotion dependency-aware attention model, which makes the best use of label information and the emotion dependency prior knowledge and the experiments on two public news datasets have proved the effectiveness of the proposed model.
EmoMix: Building an Emotion Lexicon for Compound Emotion Analysis
This work proposes an automatic building method of emotion lexicon based on the psychological theory of compound emotion that could map emotional words into an emotion space, and annotate different emotion classes through a cascade clustering algorithm.
Comparison of emotion lexicons
This paper compares frequently used emotion lexicons EmoSenticNet, and National Research Council Canada (NRC), as well as relatively newer emotion lexicon DepecheMood (DPM), and Topic based DepeCheM Mood (TDPM) to provide detailed comparison of the effects of lexicons on emotion classification process.
Identifying Emotions in Social Media: Comparison of Word-Emotion Lexicons
An algorithm is designed and implemented that applies natural language processing (NLP) techniques along with a number of heuristics that reflect the way humans naturally assess emotions in written texts over a set of Facebook and Twitter messages.
Learning from Multi-annotator Data
A noise-aware classification framework that integrates the steps of noisy label aggregation and classification is proposed that is suitable for directly running on crowdsourcing datasets and applies to various kinds of classification algorithms.
EmoMix+: An Approach of Depression Detection Based on Emotion Lexicon for Mobile Application
Emotion lexicon is an important auxiliary resource for text emotion analysis. Previous works mainly focused on positive and negative classification and less on fine-grained emotion classification.
Neural domain adaptation of sentiment lexicons
This paper proposes a neural network approach that modifies a sentiment lexicon using distantly annotated text of a certain domain and presents a completely data-driven domain characterization metric that measures the centrality of a set of documents.
The Emotion Profile of Web Search
It is hypothesised that users are more likely to click emotionally charged results than emotionless results, both in general, and in particular when their query relates to controversial topics.
Using Customer Service Dialogues for Satisfaction Analysis with Context-Assisted Multiple Instance Learning
An extensible Context-Assessment Multiple Instance Learning (CAMIL) model is proposed to predict the sentiments of all the customer utterances and then aggregate those sentiments into service satisfaction polarity and proposes a novel Context Clue Matching Mechanism (CCMM) to enhance the representations of all customer utterance with their matched context clues.
A Network Framework for Noisy Label Aggregation in Social Media
This paper focuses on the task of noisy label aggregation in social media, where users with different social or culture backgrounds may annotate invalid or malicious tags for documents, by calculating the matching degree of a document’s topics and the annotators’ meta-data.


Depeche Mood: a Lexicon for Emotion Analysis from Crowd Annotated News
This paper presents a novel approach for extracting - in a totally automated way - a high-coverage and high-precision lexicon of roughly 37 thousand terms annotated with emotion scores, called DepecheMood, which exploits in an original way 'crowd-sourced' affective annotation implicitly provided by readers of news articles from
Build Emotion Lexicon from Microblogs by Combining Effects of Seed Words and Emoticons in a Heterogeneous Graph
This paper proposes a novel emotion lexicon building framework that leverages both seed words and emoticons simultaneously to capture emotion distributions of candidate words more accurately and achieves promising results for emotion classification compared to the state-of-the-art lexicons.
A word-emoticon mutual reinforcement ranking model for building sentiment lexicon from massive collection of microblogs
It is observed that the graphical emoticons are good natural sentiment labels for the corresponding microblog posts and a word-emoticon mutual reinforcement ranking model is proposed to learn the sentiment lexicon from the massive collection of microblog data.
Build Chinese Emotion Lexicons Using A Graph-based Algorithm and Multiple Resources
A graph-based algorithm which ranks words according to a few seed emotion words, and uses multiple similarity metrics which can be derived from dictionaries, unlabeled corpora or heuristic rules is adopted.
A Non-negative Matrix Tri-factorization Approach to Sentiment Classification with Lexical Prior Knowledge
A novel approach to learn from lexical prior knowledge in the form of domain-independent sentiment-laden terms, in conjunction with domain-dependent unlabeled data and a few labeled documents is proposed.
It is shown how the combined strength and wisdom of the crowds can be used to generate a large, high‐quality, word–emotion and word–polarity association lexicon quickly and inexpensively.
Generate Adjective Sentiment Dictionary for Social Media Sentiment Analysis Using Constrained Nonnegative Matrix Factorization
An automatic sentiment dictionary generation method, called Constrained Symmetric Nonnegative Matrix Factorization (CSNMF) algorithm, to assign polarity scores to each word in the dictionary, on a large social media corpus -
Personalized Sentiment Classification Based on Latent Individuality of Microblog Users
A novel, extensible personalized sentiment classification method based on a variant of latent factor model to capture personal sentiment variations by mapping users and posts into a low-dimensional factor space and leverages users following relation to consolidate the individuality of a user fused from other users with similar interests.
Topic sentiment mixture: modeling facets and opinions in weblogs
The proposed Topic-Sentiment Mixture (TSM) model can reveal the latent topical facets in a Weblog collection, the subtopics in the results of an ad hoc query, and their associated sentiments and could also provide general sentiment models that are applicable to any ad hoc topics.
Document clustering based on non-negative matrix factorization
This paper proposes a novel document clustering method based on the non-negative factorization of the term-document matrix of the given document corpus that surpasses the latent semantic indexing and the spectral clustering methods not only in the easy and reliable derivation of document clustered results, but also in document clusters accuracies.