AHCI RESEARCH GROUP
Publications
Papers published in international journals,
proceedings of conferences, workshops and books.
OUR RESEARCH
Scientific Publications
How to
Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
2017
Gentile, Vito; Milazzo, Fabrizio; Sorce, Salvatore; Gentile, Antonio; Augello, Agnese; Pilato, Giovanni
Body Gestures and Spoken Sentences: A Novel Approach for Revealing User's Emotions Proceedings Article
In: Proceedings - IEEE 11th International Conference on Semantic Computing, ICSC 2017, pp. 69–72, Institute of Electrical and Electronics Engineers Inc., 2017, ISBN: 978-1-5090-4896-0.
Abstract | Links | BibTeX | Tags: Emotion Analysis, Emotion Recognition, Facial Expressions, Gestural user interfaces, Human computer interaction, Semantic Computing, Sentiment Analysis
@inproceedings{gentileBodyGesturesSpoken2017,
title = {Body Gestures and Spoken Sentences: A Novel Approach for Revealing User's Emotions},
author = { Vito Gentile and Fabrizio Milazzo and Salvatore Sorce and Antonio Gentile and Agnese Augello and Giovanni Pilato},
doi = {10.1109/ICSC.2017.14},
isbn = {978-1-5090-4896-0},
year = {2017},
date = {2017-01-01},
booktitle = {Proceedings - IEEE 11th International Conference on Semantic Computing, ICSC 2017},
pages = {69--72},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {In the last decade, there has been a growing interest in emotion analysis research, which has been applied in several areas of computer science. Many authors have contributed to the development of emotion recognition algorithms, considering textual or non verbal data as input, such as facial expressions, gestures or, in the case of multi-modal emotion recognition, a combination of them. In this paper, we describe a method to detect emotions from gestures using the skeletal data obtained from Kinect-like devices as input, as well as a textual description of their meaning. The experimental results show that the correlation existing between body movements and spoken user sentence(s) can be used to reveal user's emotions from gestures. textcopyright 2017 IEEE.},
keywords = {Emotion Analysis, Emotion Recognition, Facial Expressions, Gestural user interfaces, Human computer interaction, Semantic Computing, Sentiment Analysis},
pubstate = {published},
tppubtype = {inproceedings}
}
In the last decade, there has been a growing interest in emotion analysis research, which has been applied in several areas of computer science. Many authors have contributed to the development of emotion recognition algorithms, considering textual or non verbal data as input, such as facial expressions, gestures or, in the case of multi-modal emotion recognition, a combination of them. In this paper, we describe a method to detect emotions from gestures using the skeletal data obtained from Kinect-like devices as input, as well as a textual description of their meaning. The experimental results show that the correlation existing between body movements and spoken user sentence(s) can be used to reveal user's emotions from gestures. textcopyright 2017 IEEE.
Milazzo, Fabrizio; Augello, Agnese; Pilato, Giovanni; Gentile, Vito; Gentile, Antonio; Sorce, Salvatore
Exploiting Correlation between Body Gestures and Spoken Sentences for Real-Time Emotion Recognition Proceedings Article
In: ACM International Conference Proceeding Series, Association for Computing Machinery, 2017, ISBN: 978-1-4503-5237-6.
Abstract | Links | BibTeX | Tags: Emotion Recognition, Gestural user interfaces, Human computer interaction, Sentiment Analysis
@inproceedings{milazzoExploitingCorrelationBody2017,
title = {Exploiting Correlation between Body Gestures and Spoken Sentences for Real-Time Emotion Recognition},
author = { Fabrizio Milazzo and Agnese Augello and Giovanni Pilato and Vito Gentile and Antonio Gentile and Salvatore Sorce},
doi = {10.1145/3125571.3125590},
isbn = {978-1-4503-5237-6},
year = {2017},
date = {2017-01-01},
booktitle = {ACM International Conference Proceeding Series},
volume = {Part F131371},
publisher = {Association for Computing Machinery},
abstract = {Humans communicate their affective states through different media, both verbal and non-verbal, often used at the same time. The knowledge of the emotional state plays a key role to provide personalized and context-related information and services. This is the main reason why several algorithms have been proposed in the last few years for the automatic emotion recognition. In this work we exploit the correlation between one's affective state and the simultaneous body expressions in terms of speech and gestures. Herewe propose a system for real-Time emotion recognition from gestures. In a first step, the system builds a trusted dataset of association pairs (motion datatextrightarrow emotion pattern), also based on textual information. Such dataset is the ground truth for a further step, where emotion patterns can be extracted from new unclassified gestures. Experimental results demonstrate a good recognition accuracy and real-Time capabilities of the proposed system. textcopyright 2017 Copyright held by the owner/author(s).},
keywords = {Emotion Recognition, Gestural user interfaces, Human computer interaction, Sentiment Analysis},
pubstate = {published},
tppubtype = {inproceedings}
}
Humans communicate their affective states through different media, both verbal and non-verbal, often used at the same time. The knowledge of the emotional state plays a key role to provide personalized and context-related information and services. This is the main reason why several algorithms have been proposed in the last few years for the automatic emotion recognition. In this work we exploit the correlation between one's affective state and the simultaneous body expressions in terms of speech and gestures. Herewe propose a system for real-Time emotion recognition from gestures. In a first step, the system builds a trusted dataset of association pairs (motion datatextrightarrow emotion pattern), also based on textual information. Such dataset is the ground truth for a further step, where emotion patterns can be extracted from new unclassified gestures. Experimental results demonstrate a good recognition accuracy and real-Time capabilities of the proposed system. textcopyright 2017 Copyright held by the owner/author(s).
2014
Sangiorgi, Pierluca; Augello, Agnese; Pilato, Giovanni
An Approach to Detect Polarity Variation Rules for Sentiment Analysis Proceedings Article
In: WEBIST 2014 - Proceedings of the 10th International Conference on Web Information Systems and Technologies, pp. 344–349, SciTePress, 2014, ISBN: 978-989-758-024-6.
Abstract | Links | BibTeX | Tags: Opinion Mining, Sentiment Analysis
@inproceedings{sangiorgiApproachDetectPolarity2014,
title = {An Approach to Detect Polarity Variation Rules for Sentiment Analysis},
author = { Pierluca Sangiorgi and Agnese Augello and Giovanni Pilato},
doi = {10.5220/0004961903440349},
isbn = {978-989-758-024-6},
year = {2014},
date = {2014-01-01},
booktitle = {WEBIST 2014 - Proceedings of the 10th International Conference on Web Information Systems and Technologies},
volume = {2},
pages = {344--349},
publisher = {SciTePress},
abstract = {Sentiment Analysis is a discipline that aims at identifying and extract the subjectivity expressed by authors of information sources. Sentiment Analysis can be applied at different level of granularity and each of them still has open issues. In this paper we propose a completely unsupervised approach aimed at inducing a set of words patterns that change the polarity of subjective terms. This is a very important task because, while sentiment lexicons are valid tools that can be used to identify the polarity at word level, working at different level of granularity they are no longer sufficient, because of the various aspects to consider like the context, the use of negations and so on that can change the polarity of subjective terms.},
keywords = {Opinion Mining, Sentiment Analysis},
pubstate = {published},
tppubtype = {inproceedings}
}
Sentiment Analysis is a discipline that aims at identifying and extract the subjectivity expressed by authors of information sources. Sentiment Analysis can be applied at different level of granularity and each of them still has open issues. In this paper we propose a completely unsupervised approach aimed at inducing a set of words patterns that change the polarity of subjective terms. This is a very important task because, while sentiment lexicons are valid tools that can be used to identify the polarity at word level, working at different level of granularity they are no longer sufficient, because of the various aspects to consider like the context, the use of negations and so on that can change the polarity of subjective terms.
Terrana, Diego; Augello, Agnese; Pilato, Giovanni
Analysis of Facebook Users' Relationships Through Sentiment Classification: A Case Study of Italian Politicians Journal Article
In: International Journal of Semantic Computing, vol. 8, no. 3, pp. 301–317, 2014, ISSN: 1793351X.
Abstract | Links | BibTeX | Tags: Facebook, Sentiment Analysis, User Profiling
@article{terranaAnalysisFacebookUsers2014,
title = {Analysis of Facebook Users' Relationships Through Sentiment Classification: A Case Study of Italian Politicians},
author = { Diego Terrana and Agnese Augello and Giovanni Pilato},
doi = {10.1142/S1793351X14400108},
issn = {1793351X},
year = {2014},
date = {2014-01-01},
journal = {International Journal of Semantic Computing},
volume = {8},
number = {3},
pages = {301--317},
abstract = {We illustrate a system that analyzes the homepage of a Facebook user or group in order to automatically detect who has discussed what and how it has been discussed. We have focused the analysis on three main actors of Italian politics. The goal is to find people who agree or disagree about given topics with the owner of the Facebook page under analysis. All public posts shared by a user are retrieved by an ad hoc built crawler. Information such as 'posts', 'comments', 'likes', are extracted from the Facebook page. Each post is classified as belonging to a set of predefined categories and its sentiment is also detected as being positive, negative or neutral. All the comments to that post are therefore analyzed and categorized together with its sentiment polarity. For each Facebook user under analysis a statistics of the topics dealt with is made, and for each category a graph is created where the concordance of sentiment is highlighted between the posts belonging to a given class and the related comments of the people interacting with the user or group under analysis. The graph can therefore be used to profile the user relationships according to sentiment classification. textcopyright 2014 World Scientific Publishing Company.},
keywords = {Facebook, Sentiment Analysis, User Profiling},
pubstate = {published},
tppubtype = {article}
}
We illustrate a system that analyzes the homepage of a Facebook user or group in order to automatically detect who has discussed what and how it has been discussed. We have focused the analysis on three main actors of Italian politics. The goal is to find people who agree or disagree about given topics with the owner of the Facebook page under analysis. All public posts shared by a user are retrieved by an ad hoc built crawler. Information such as 'posts', 'comments', 'likes', are extracted from the Facebook page. Each post is classified as belonging to a set of predefined categories and its sentiment is also detected as being positive, negative or neutral. All the comments to that post are therefore analyzed and categorized together with its sentiment polarity. For each Facebook user under analysis a statistics of the topics dealt with is made, and for each category a graph is created where the concordance of sentiment is highlighted between the posts belonging to a given class and the related comments of the people interacting with the user or group under analysis. The graph can therefore be used to profile the user relationships according to sentiment classification. textcopyright 2014 World Scientific Publishing Company.
Terrana, Diego; Augello, Agnese; Pilato, Giovanni
Automatic Unsupervised Polarity Detection on a Twitter Data Stream Proceedings Article
In: Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014, pp. 128–134, IEEE Computer Society, 2014, ISBN: 978-1-4799-4002-8.
Abstract | Links | BibTeX | Tags: Data Mining, Opinion Mining, Semantic Computing, Sentiment Analysis
@inproceedings{terranaAutomaticUnsupervisedPolarity2014,
title = {Automatic Unsupervised Polarity Detection on a Twitter Data Stream},
author = { Diego Terrana and Agnese Augello and Giovanni Pilato},
doi = {10.1109/ICSC.2014.17},
isbn = {978-1-4799-4002-8},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014},
pages = {128--134},
publisher = {IEEE Computer Society},
abstract = {In this paper we propose a simple and completely automatic methodology for analyzing sentiment of users in Twitter. Firstly, we built a Twitter corpus by grouping tweets expressing positive and negative polarity through a completely automatic procedure by using only emoticons in tweets. Then, we have built a simple sentiment classifier where an actual stream of tweets from Twitter is processed and its content classified as positive, negative or neutral. The classification is made without the use of any pre-defined polarity lexicon. The lexicon is automatically inferred from the streaming of tweets. Experimental results show that our method reduces human intervention and, consequently, the cost of the whole classification process. We observe that our simple system captures polarity distinctions matching reasonably well the classification done by human judges. textcopyright 2014 IEEE.},
keywords = {Data Mining, Opinion Mining, Semantic Computing, Sentiment Analysis},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper we propose a simple and completely automatic methodology for analyzing sentiment of users in Twitter. Firstly, we built a Twitter corpus by grouping tweets expressing positive and negative polarity through a completely automatic procedure by using only emoticons in tweets. Then, we have built a simple sentiment classifier where an actual stream of tweets from Twitter is processed and its content classified as positive, negative or neutral. The classification is made without the use of any pre-defined polarity lexicon. The lexicon is automatically inferred from the streaming of tweets. Experimental results show that our method reduces human intervention and, consequently, the cost of the whole classification process. We observe that our simple system captures polarity distinctions matching reasonably well the classification done by human judges. textcopyright 2014 IEEE.
Terrana, Diego; Augello, Agnese; Pilato, Giovanni
Facebook Users Relationships Analysis Based on Sentiment Classification Proceedings Article
In: Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014, pp. 290–296, IEEE Computer Society, 2014, ISBN: 978-1-4799-4002-8.
Abstract | Links | BibTeX | Tags: Facebook, Semantic Computing, Sentiment Analysis, User Profiling
@inproceedings{terranaFacebookUsersRelationships2014,
title = {Facebook Users Relationships Analysis Based on Sentiment Classification},
author = { Diego Terrana and Agnese Augello and Giovanni Pilato},
doi = {10.1109/ICSC.2014.59},
isbn = {978-1-4799-4002-8},
year = {2014},
date = {2014-01-01},
booktitle = {Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014},
pages = {290--296},
publisher = {IEEE Computer Society},
abstract = {It is presented an approach aimed at analyzing the homepage of a Facebook user or group in order to automatically detect who has discussed what and how it has been discussed. All public posts shared by an user are retrieved by an ad hoc built crawler. Information such as a text messages, comments, likes, is extracted for each post. Each post is classified as belonging to a set of predefined categories and its sentiment is also detected as being positive, negative or neutral. All the comments to that post are therefore analyzed and categorized together with its sentiment polarity. For each category it is created a graph where it is highlighted the concordance of sentiment between the posts and the related comments. The graph can be therefore used to profile the user relationships according to sentiment classification. textcopyright 2014 IEEE.},
keywords = {Facebook, Semantic Computing, Sentiment Analysis, User Profiling},
pubstate = {published},
tppubtype = {inproceedings}
}
It is presented an approach aimed at analyzing the homepage of a Facebook user or group in order to automatically detect who has discussed what and how it has been discussed. All public posts shared by an user are retrieved by an ad hoc built crawler. Information such as a text messages, comments, likes, is extracted for each post. Each post is classified as belonging to a set of predefined categories and its sentiment is also detected as being positive, negative or neutral. All the comments to that post are therefore analyzed and categorized together with its sentiment polarity. For each category it is created a graph where it is highlighted the concordance of sentiment between the posts and the related comments. The graph can be therefore used to profile the user relationships according to sentiment classification. textcopyright 2014 IEEE.
2013
Mazzonello, Valentina; Gaglio, Salvatore; Augello, Agnese; Pilato, Giovanni
A Study on Classification Methods Applied to Sentiment Analysis Proceedings Article
In: Proceedings - 2013 IEEE 7th International Conference on Semantic Computing, ICSC 2013, pp. 426–431, 2013, ISBN: 978-0-7695-5119-7.
Abstract | Links | BibTeX | Tags: Sentiment Analysis
@inproceedings{mazzonelloStudyClassificationMethods2013,
title = {A Study on Classification Methods Applied to Sentiment Analysis},
author = { Valentina Mazzonello and Salvatore Gaglio and Agnese Augello and Giovanni Pilato},
doi = {10.1109/ICSC.2013.82},
isbn = {978-0-7695-5119-7},
year = {2013},
date = {2013-01-01},
booktitle = {Proceedings - 2013 IEEE 7th International Conference on Semantic Computing, ICSC 2013},
pages = {426--431},
abstract = {Sentiment analysis is a new area of research in data mining that concerns the detection of opinions and/or sentiments in texts. This work focuses on the application and the comparison of three classification techniques over a text corpus composed of reviews of commercial products in order to detect opinions about them. The chosen domain is about perfumes, and user opinions composing the corpus are written in Italian language. The proposed approach is completely data-driven: a Term Frequency / Inverse Document Frequency (TFIDF) terms selection procedure has been applied in order to make computation more efficient, to improve the classification results and to manage some issues related to the specific classification procedure adopted. textcopyright 2013 IEEE.},
keywords = {Sentiment Analysis},
pubstate = {published},
tppubtype = {inproceedings}
}
Sentiment analysis is a new area of research in data mining that concerns the detection of opinions and/or sentiments in texts. This work focuses on the application and the comparison of three classification techniques over a text corpus composed of reviews of commercial products in order to detect opinions about them. The chosen domain is about perfumes, and user opinions composing the corpus are written in Italian language. The proposed approach is completely data-driven: a Term Frequency / Inverse Document Frequency (TFIDF) terms selection procedure has been applied in order to make computation more efficient, to improve the classification results and to manage some issues related to the specific classification procedure adopted. textcopyright 2013 IEEE.
Sangiorgi, Pierluca; Augello, Agnese; Pilato, Giovanni
An Unsupervised Data-Driven Cross-Lingual Method for Building High Precision Sentiment Lexicons Proceedings Article
In: Proceedings - 2013 IEEE 7th International Conference on Semantic Computing, ICSC 2013, pp. 184–190, 2013, ISBN: 978-0-7695-5119-7.
Abstract | Links | BibTeX | Tags: Natural Language Processing, Sentiment Analysis
@inproceedings{sangiorgiUnsupervisedDatadrivenCrosslingual2013,
title = {An Unsupervised Data-Driven Cross-Lingual Method for Building High Precision Sentiment Lexicons},
author = { Pierluca Sangiorgi and Agnese Augello and Giovanni Pilato},
doi = {10.1109/ICSC.2013.40},
isbn = {978-0-7695-5119-7},
year = {2013},
date = {2013-01-01},
booktitle = {Proceedings - 2013 IEEE 7th International Conference on Semantic Computing, ICSC 2013},
pages = {184--190},
abstract = {In this paper we present a completely unsupervised approach for creating a sentiment lexicon. The approach has been realized by designing a pipeline which implements an unsupervised system that covers different aspects: the automatic extraction of user reviews, the pre-processing of text, the use of a scoring measure which combines: entropy, term frequency, inverse document frequency, and finally a cross lingual intersection. We have validated the approach though the analysis of a previews present in the Google Play market. The results show the effectiveness of the approach given by satisfactory values of precision for the obtained lexicon. textcopyright 2013 IEEE.},
keywords = {Natural Language Processing, Sentiment Analysis},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper we present a completely unsupervised approach for creating a sentiment lexicon. The approach has been realized by designing a pipeline which implements an unsupervised system that covers different aspects: the automatic extraction of user reviews, the pre-processing of text, the use of a scoring measure which combines: entropy, term frequency, inverse document frequency, and finally a cross lingual intersection. We have validated the approach though the analysis of a previews present in the Google Play market. The results show the effectiveness of the approach given by satisfactory values of precision for the obtained lexicon. textcopyright 2013 IEEE.