Filters








11,925 Hits in 2.9 sec

Analyzing Sentiment in Classical Chinese Poetry

Yufang Hou, Anette Frank
2015 Proceedings of the 9th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities (LaTeCH)  
We evaluate our lexicon intrinsically and extrinsically.  ...  In this paper, we propose a weakly supervised approach based on Weighted Personalized PageRank (WPPR) to create a sentiment lexicon for classical Chinese poetry.  ...  The work presented in this paper provides a quantitative means to study sentiment in classical Chinese poetry.  ... 
doi:10.18653/v1/w15-3703 dblp:conf/latech/HouF15 fatcat:ftgtdsdmtvav5an5zihxaahrae

A unified graph model for Chinese product review summarization using richer information

He Huang, Chunping Li
2012 Proceedings of the First International Workshop on Issues of Sentiment Discovery and Opinion Mining - WISDOM '12  
In this paper, we present a novel unified graph model, composited information graph (CIG), to represent reviews with lexical, topic and together with sentiment information.  ...  We use probabilistic methods to model the lexical, topic and sentiment information separately, associate with the discovered information in the CIG model, and generate summaries with a HITS-like algorithm  ...  Building the CIG Model With the lexical, topic and sentiment information of sentences, we start to build the CIG model.  ... 
doi:10.1145/2346676.2346678 fatcat:6v6xy2jhiffwhm6lgks4tcotju

SENTI2VEC: AN EFFECTIVE FEATURE EXTRACTION TECHNIQUE FOR SENTIMENT ANALYSIS BASED ON WORD2VEC

Eissa M.Alshari, Azreen Azman, Shyamala Doraisamy, Norwati Mustapha, Mostafa Alksher
2020 Malaysian Journal of Computer Science  
This paper also investigates the effect of two opinion lexical dictionaries on the performance of sentiment analysis, and one of the dictionaries are created based on SentiWordNet.  ...  The discovery of an active feature extraction technique has been the focus of many researchers to improve the performance of classification methods, such as for sentiment analysis.  ...  The users have to evaluate many similar products with different features, quality, and prices before making a purchase decision.  ... 
doi:10.22452/mjcs.vol33no3.5 fatcat:2t3iuxxzujb4hjjqkqwgweifqq

A Cross-Lingual Approach for Building Multilingual Sentiment Lexicons [chapter]

Behzad Naderalvojoud, Behrang Qasemizadeh, Laura Kallmeyer, Ebru Akcapinar Sezer
2018 Lecture Notes in Computer Science  
We propose a cross-lingual distributional model to build sentiment lexicons in many languages from resources available in English.  ...  We evaluate our proposed method for two languages, German and Turkish, and several tasks.  ...  To evaluate our method for building sentiment lexicons, we employ a lexiconbased deep learning method based on BiLSTM proposed in [14] for sentiment classification.  ... 
doi:10.1007/978-3-030-00794-2_28 fatcat:fyohlxw4urgbpeodavh2rbzfha

Corpus Statistics in Text Classification of Online Data [article]

Marina Sokolova, Victoria Bobicev
2018 arXiv   pre-print
Our empirical results are obtained for a multi-class sentiment analysis application.  ...  In the current work, we investigate how corpus characteristics of textual data sets correspond to text classification results.  ...  Text Classification Experiments In our study we represented texts through a) Bag of words (BOW) features, b) sentiment-bearing features, and c) features selected from the two feature sets: a) to build  ... 
arXiv:1803.06390v1 fatcat:y6w6a4ykxbc6rafavgnqveu44q

Sentiment Analysis in Microblogs Using HMMs with Syntactic and Sentimental Information

Noo-Ri Kim, Kyoungmin Kim, Jee-Hyong Lee
2017 International Journal of Fuzzy Logic and Intelligent Systems  
Our proposed approach first identifies groups of words that have similar syntactic and sentimental roles, called SIGs (similar syntactic and sentimental information groups).  ...  We then build HMMs using the SIGs as hidden states for the initialization. The SIGs function as the prior knowledge of formative elements of sentimental sentences for HMMs.  ...  We first build positive syntactic-sentimental feature vectors of unigrams with positive instances. Then we apply GMMs to group unigrams into SIGs. We build SIGs for the negative HMM in a similar way.  ... 
doi:10.5391/ijfis.2017.17.4.329 fatcat:itc5pnacnvc35ijeizdwux2doy

Subjectivity and Sentiment Analysis of Arabic: A Survey [chapter]

Mohammed Korayem, David Crandall, Muhammad Abdul-Mageed
2012 Communications in Computer and Information Science  
Subjectivity and sentiment analysis (SSA) has recently gained considerable attention, but most of the resources and systems built so far are tailored to English and other Indo-European languages.  ...  Elhawary and Elfeky [19] used the similarity graph to build an Arabic lexicon.  ...  They build an Arabic lexicon based on a similarity graph for use with the sentiment component.  ... 
doi:10.1007/978-3-642-35326-0_14 fatcat:vn7jut5g5ffprgwrlfmdd4apqq

Weakly supervised techniques for domain-independent sentiment classification

Jonathon Read, John Carroll
2009 Proceeding of the 1st international CIKM workshop on Topic-sentiment analysis for mass opinion - TSA '09  
The results indicate that the word similarity techniques are suitable for applications that require sentiment classification across several domains.  ...  This paper presents experiments that investigate the effectiveness of word similarity techniques when performing weakly-supervised sentiment classification.  ...  Scoring Sentences According to Strength of Sentiment This section reports experiments that evaluate the efficacy of the word similarity methods in a reproduction of SemEval 2007's shared task on Affective  ... 
doi:10.1145/1651461.1651470 fatcat:gx4nfxrranfulls77kz4j5klmq

Building an Arabic Sentiment Lexicon Using Semi-supervised Learning

Fawaz H.H. Mahyoub, Muazzam A. Siddiqui, Mohamed Y. Dahab
2014 Journal of King Saud University: Computer and Information Sciences  
A number of lexical resources are available to facilitate this task in English. One such resource is the SentiWordNet, which assigns sentiment scores to words found in the English WordNet.  ...  The lexicon was evaluated by incorporating it into a machine learning-based classifier.  ...  Elhawary and Elfeky (2010) used a similarity graph to build an Arabic lexicon.  ... 
doi:10.1016/j.jksuci.2014.06.003 fatcat:jljfjb2vlfgrzogdtbddnokjhm

Enhancing Embedding-Based Chinese Word Similarity Evaluation with Concepts and Synonyms Knowledge

Fulian Yin, Yanyan Wang, Jianbo Liu, Meiqi Ji
2020 CMES - Computer Modeling in Engineering & Sciences  
information to enhance word similarity evaluation.  ...  To address these above problems, we propose an enhancing embedding-based word similarity evaluation with character-word concepts and synonyms knowledge, namely EWS-CS model, which can provide extra semantic  ...  As for each evaluation dataset D ¼ w The key to the evaluation of the similarity task is to find the correlation between the two sequences.  ... 
doi:10.32604/cmes.2020.010579 fatcat:wtr4w56bfvcufkoomcjprviple

Semantic frames as an anchor representation for sentiment analysis

Josef Ruppenhofer, Ines Rehbein
2012 Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis  
In the paper, we propose SentiFrameNet, an extension to FrameNet, as a novel representation for sentiment analysis that is tailored to these aims.  ...  Current work on sentiment analysis is characterized by approaches with a pragmatic focus, which use shallow techniques in the interest of robustness but often rely on ad-hoc creation of data sets and methods  ...  For a similar representation of multiple opinions in a Dutch lexical resource, see (Maks and Vossen, 2011) .  ... 
dblp:conf/wassa/RuppenhoferR12 fatcat:aq4lcangd5fy7b5al2ocrmpxgq

Sentiment Analysis and Similarity Evaluation for Heterogeneous-Domain Product Reviews

Mangal Singh, Tabrez Nafis, Neel Mani
2016 International Journal of Computer Applications  
For each review, an intermediate form is calculated using sentiment vectors which is further processed to calculate the sentiment polarity magnitude and similarity of reviews.  ...  We defined a framework to classify heterogeneous product reviews with degree of polarity on a sentiment scale of range -2 to 2.  ...  Semantic similarity between words like nouns and verbs can easily evaluated using WordNet and thus it is used to build emotion vocabulary.  ... 
doi:10.5120/ijca2016910112 fatcat:pki5z34bunct7odoq4mbrmhbmu

Text-Based User-kNN: Measuring User Similarity Based on Text Reviews [chapter]

Maria Terzi, Matthew Rowe, Maria-Angela Ferrario, Jon Whittle
2014 Lecture Notes in Computer Science  
We investigate the performance of text semantic similarity measures and we evaluate our text-based user-kNN approach by comparing it to a range of ratings-based approaches in a ratings prediction task.  ...  This article reports on a modification of the user-kNN algorithm that measures the similarity between users based on the similarity of text reviews, instead of ratings.  ...  In user-kNN approaches, similar to our work, research exploiting text reviews is limited to applying sentiment analysis on text reviews [3, 4] , or building user profiles of feature preferences extracted  ... 
doi:10.1007/978-3-319-08786-3_17 fatcat:o4um5urzx5g7do3qcwnqrs2224

Weakly-supervised Appraisal Analysis

Jonathon Read, John Carroll
2012 Linguistic Issues in Language Technology  
We evaluate the method's performance using a collection of book reviews annotated according to the Appraisal theory.  ...  To analyse text according to the theory we employ a weakly-supervised approach to text classification, which involves comparing the similarity of words with prototypical examples of classes.  ...  We are very grateful to David Hope, for his help in annotating the book review corpus.  ... 
doi:10.33011/lilt.v8i.1307 fatcat:2bt5w2hzyndc3glnphbzzyl4lq

Using Automated Lexical Resources In Arabic Sentence Subjectivity

Hanaa Mobarz, Mohsen Rashown, Ibrahim Farag
2014 International Journal of Artificial Intelligence & Applications  
A common point in almost any work on Sentiment analysis is the need to identify which elements of language (words) contribute to express the subjectivity in text.  ...  Collecting of these elements (sentiment words) regardless the context with their polarities (positive/negative) is called sentiment lexical resources or subjective lexicon.  ...  RELATED WORK In this section, we will present the most notable research work on building English sentiment lexicons and previous attempts to build Arabic sentiment lexicons.  ... 
doi:10.5121/ijaia.2014.5601 fatcat:k3w3wphvkfbaxoxqralbxla7lm
« Previous Showing results 1 — 15 out of 11,925 results