10,918 Hits in 5.7 sec

A benchmark study on sentiment analysis for software engineering research

Nicole Novielli, Daniela Girardi, Filippo Lanubile
2018 Proceedings of the 15th International Conference on Mining Software Repositories - MSR '18  
A recent research trend has emerged to identify developers' emotions, by applying sentiment analysis to the content of communication traces left in collaborative development environments.  ...  In this paper, we report a benchmark study to assess the performance and reliability of three sentiment analysis tools specifically customized for software engineering.  ...  ACKNOWLEDGMENTS This work is partially funded by the project 'EmoQuest -Investigating the Role of Emotions in Online Question & Answer Sites', funded by MIUR (Ministero dell'Università e della Ricerca)  ... 
doi:10.1145/3196398.3196403 dblp:conf/msr/NovielliGL08 fatcat:g2s6ye5uvnaill2ys7pxdid4p4

Detecting Vocal Irony [chapter]

Felix Burkhardt, Benjamin Weiss, Florian Eyben, Jun Deng, Björn Schuller
2018 Lecture Notes in Computer Science  
Baseline results show that an ironic voice can be detected automatically solely based on acoustic features in 69.3 UAR (unweighted average recall) and anger with 64.1 UAR.  ...  We describe a data collection for vocal expression of ironic utterances and anger based on an Android app that was specifically developed for this study.  ...  Normalisation of EWE weights to sum 1 and min and max. correlations to 0 and 1 Computation of final EWE average rating by weighted average using EWE weights In Tables 1 and 2 , the pairwise rater agreements  ... 
doi:10.1007/978-3-319-73706-5_2 fatcat:e73jt3eqhbfwvjex7xwiz23s6i

Sentic API: A Common and Common-Sense Knowledge API for Cognition-Driven Sentiment Analysis

Erik Cambria, Soujanya Poria, Alexander F. Gelbukh, Kenneth Kwok
2014 Workshop on Making Sense of Microposts  
Working at concept-level is important for tasks such as opinion mining, especially in the case of microblogging analysis.  ...  In this work, we present Sentic API, a common-sense based application programming interface for concept-level sentiment analysis, which provides semantics and sentics (that is, denotative and connotative  ...  We then use the resulting SBoC as input for the Sentic API and look up into it in order to obtain the relative sentic vectors, which we average in order to detect primary and secondary moods conveyed by  ... 
dblp:conf/msm/CambriaPGK14 fatcat:wcp6y5lkojhqxkpkbvb7el3cw4

An Emotion-driven Approach for Aspect-based Opinion Mining

Marco Polignano, Pierpaolo Basile, Marco de Gemmis, Giovanni Semeraro
2018 Italian Information Retrieval Workshop  
In this work, we present an approach of text mining for detecting the topic of discussion for textual contents and the emotion that the writer feels while writing it.  ...  Conversely to the classic strategies of sentiment analysis, we enrich the standard polarity prediction task with more fine-grained information about user's emotion.  ...  This counting is used for defining an order of the most probable emotion associated with the phrase.  ... 
dblp:conf/iir/PolignanoBGS18 fatcat:s6kl2r7npvbhvhmuje6fakksqi

The Anatomy of Brexit Debate on Facebook [article]

Michela Del Vicario, Fabiana Zollo, Guido Caldarelli, Antonio Scala, Walter Quattrociocchi
2016 arXiv   pre-print
We compare how the same topics are presented on posts and the related emotional response on comments finding significant differences in both echo chambers and that polarization influences the perception  ...  This pattern elicits the formation of polarized groups -- i.e., echo chambers -- where the interaction with like-minded people might even reinforce polarization.  ...  Then, for each concept, we consider the emotional distance between the average sentiment of the post and that of its users.  ... 
arXiv:1610.06809v1 fatcat:5i2jzwjysjcnzkxs5asnfuy7r4

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

Erik Cambria, Daniel Olsher, Dheeraj Rajagopal
SenticNet is a publicly available semantic and affective resource for concept-level sentiment analysis.  ...  In order to infer the polarity of a sentence, in fact, an opinion mining engine only needs to extract the features or aspects of the discussed service or product, e.g., size or weight of a phone, and the  ...  tasks such as feature spotting and polarity detection, respectively.  ... 
doi:10.1609/aaai.v28i1.8928 fatcat:jpv354vv6zalviswxatiidd3oa

Intelligent emotion detection method based on deep learning in medical and health data

Jianqiang Xu, Zhujiao Hu, Junzhong Zou, Anqi Bi
2019 IEEE Access  
In order to solve the problem, an emotion detection method based on deep learning in medical and health data is proposed in this paper.  ...  In the system, multi-channel convolutional aotoencoder neural network is used to extract electrocardiograms (ECG) data features and emotional text features for emotional fatigue detection.  ...  FIGURE 4 . 4 Accuracy of emotional fatigue detection in volunteers. FIGURE 5 . 5 Average accuracy rate of emotional fatigue detection.  ... 
doi:10.1109/access.2019.2961139 fatcat:p2fqw575efhvhmn33upwgvkvsi

Detecting Controversies in Online News Media

Kaspar Beelen, Evangelos Kanoulas, Bob van de Velde
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
is paper sets out to detect controversial news reports using online discussions as a source of information.  ...  We de ne controversy as a public discussion that divides society and demonstrate that a content and stylometric analysis of these debates yields useful signals for extracting disputed news items.  ...  For each article we obtained three annotations. ose with an average higher than 2.5 were categorized as "controversial".  ... 
doi:10.1145/3077136.3080723 dblp:conf/sigir/BeelenKV17 fatcat:kr6ncntkejgc7b26cd3x5vmbai

Networks and emotion-driven user communities at popular blogs

M. Mitrović, G. Paltoglou, B. Tadić
2010 European Physical Journal B : Condensed Matter Physics  
With the machine learning methods we classify the texts of posts and comments for their emotional contents as positive or negative, or otherwise objective (neutral).  ...  Using the spectral methods of weighted bipartite graphs, we identify topological communities featuring the users clustered around certain popular posts, and underly the role of emotional contents in the  ...  A high value of L gives more weight to lower n-grams, which is usually appropriate for smaller training sets, where the probability of encountering a higher order n-gram is small.  ... 
doi:10.1140/epjb/e2010-00279-x fatcat:zw65s6no2zfb5jbbbh5aegx7zi

Detecting the magnitude of depression in Twitter users using sentiment analysis

Jini Jojo Stephen, Prabu P.
2019 International Journal of Electrical and Computer Engineering (IJECE)  
The purpose of this paper is to propose an efficient method that can detect the level of depression in Twitter users.  ...  Sentiment scores calculated can be combined with different emotions to provide a better method to calculate depression scores.  ...  Prabu P, for his constant support throughout the lifecycle of this research.  ... 
doi:10.11591/ijece.v9i4.pp3247-3255 fatcat:kerkcg4enndrxnoo7tarm6i7kq

Public discourse and news consumption on online social media: A quantitative, cross-platform analysis of the Italian Referendum [article]

Michela Del Vicario, Sabrina Gaito, Walter Quattrociocchi, Matteo Zignani, Fabiana Zollo
2017 arXiv   pre-print
Our results provide interesting insights for the understanding of the evolution of the core narratives behind different echo chambers and for the early detection of massive viral phenomena around false  ...  We measure the distance between how a certain topic is presented in the posts/tweets and the related emotional response of users.  ...  Figure 4a shows, for each entity, the average sentiment in each community (green dots fo C1, red for C2, and blue for C3) and the mean emotional distance (yellow diamonds) among communities on Facebook  ... 
arXiv:1702.06016v2 fatcat:kbzwxpzqlra5xnqgtzofv7agj4

Sentiment Analysis of Rumor Spread Amid COVID-19: Based on Weibo Text

Peng Wang, Huimin Shi, Xiaojie Wu, Longzhen Jiao
2021 Healthcare  
Driven by people's psychology of conformity, panic, group polarization, etc., various rumors appeared and spread wildly, and the Internet became a hotbed of rumors. (2) Methods: the study selected Weibo  ...  polarity and found negative sentiment and rumor spread was causally interrelated. (4) Conclusion: These findings could help us to intuitively understand the impact of rumors spread on people's emotions  ...  Then, through the weighted sum of the emotional value of the key sentence, the average value obtained is the emotional tendency value of the texts.  ... 
doi:10.3390/healthcare9101275 pmid:34682955 fatcat:haktdfdv75fxnbelrxjw24oxpa

Big Data-Driven Product Innovation Design Modeling and System Construction Method

Huicong Xue, Depei Wu, Wen-Tsao Pan
2022 Mathematical Problems in Engineering  
In order to improve the image quality of innovative design of manufacturing products, reduce the dependence on experts, increase the amount of research data, and accurately sort and select the best alternatives  ...  The average absolute value of DOD phrase in BP neural network is 0.0765, which is lower than the MLR method, and the performance of the former is better than the latter.  ...  Among them, the expression of emotional tendency of perceptual words is shown as follows: EO(word) � (EP, EI). (5) In ( 5 ), EP, EO, and EI represent emotional polarity, emotional tendency, and emotional  ... 
doi:10.1155/2022/4358330 fatcat:4rd3tmxlurhb5omaky26z2ll24

An Agent-Based Model of Opinion Polarization Driven by Emotions

Frank Schweitzer, Tamas Krivachy, David Garcia
2020 Complexity  
We derive the critical conditions for emotional interactions to obtain either consensus or polarization of opinions.  ...  with the emotion.  ...  D.G. acknowledges funding from the Vienna Science and Technology Fund through the Vienna Research Group Grant "Emotional Well-Being in the Digital Society" (VRG16-005).  ... 
doi:10.1155/2020/5282035 fatcat:dcjomyhw3jhzll4apdct7try74

Sentic patterns: Dependency-based rules for concept-level sentiment analysis

Soujanya Poria, Erik Cambria, Grégoire Winterstein, Guang-Bin Huang
2014 Knowledge-Based Systems  
properly detecting the polarity conveyed by natural language opinions.  ...  detection.  ...  Beyond emotion detection, the Hourglass model is also used for polarity detection tasks.  ... 
doi:10.1016/j.knosys.2014.05.005 fatcat:awgw4u7uobg6roujumzf6hqvzq
« Previous Showing results 1 — 15 out of 10,918 results