Publications

Conferences and Journals


  • Kalamatianos, G., Symeonidis, S., Mallis, D. & Arampatzis, A. Towards the creation of an emotion lexicon for microblogging. IN Journal of systems and information technology, .. doi:10.1108/JSIT-06-2017-0040
    [BibTeX] [Abstract] [Download PDF]

    Purpose The rapid growth of social media has rendered opinion and sentiment mining an important area of research with a wide range of applications. This research focuses on the Greek language and the microblogging platform Twitter, investigating methods for extracting emotion of individual tweets as well as population emotion for different subjects (hashtags). Design/methodology/approach The authors propose and investigate the use of emotion lexicon-based methods as a mean of extracting emotion/sentiment information from social media. We compare several approaches for measuring the intensity of six emotions: anger, disgust, fear, happiness, sadness, and surprise. To evaluate the effectiveness of our methods, we develop a benchmark dataset of tweets, manually rated by two humans Findings Development of a new sentiment lexicon for use in web applications. We then assess the performance of our methods with the new lexicon and find improved results. Research limitations/implications Automated emotion results of research seem promising and correlate to real user emotion. At this point the authors make some interesting observations about the lexicon-based approach which lead to the need for a new, better, emotion lexicon Practical implications The authors examine the variation of emotion intensity over time for selected hashtags, and associate it with real-world events. Originality/value The originality in this research is the development of a training set of tweets, manually annotated by two independent raters. We `transfer’ the sentiment information of these annotated tweets, in a meaningful way, to the set of words that appear in them.

    @article{doi:10.1108/JSIT-06-2017-0040,
    author = {Georgios Kalamatianos and Symeon Symeonidis and Dimitrios Mallis and Avi Arampatzis},
    title = {Towards the creation of an emotion lexicon for microblogging},
    journal = {Journal of Systems and Information Technology},
    volume = {0},
    number = {ja},
    pages = {00-00},
    year = {0},
    doi = {10.1108/JSIT-06-2017-0040},
    URL = {
    https://doi.org/10.1108/JSIT-06-2017-0040
    },
    eprint = {
    https://doi.org/10.1108/JSIT-06-2017-0040},
    abstract = { Purpose The rapid growth of social media has rendered opinion and sentiment mining an important area of research with a wide range of applications. This research focuses on the Greek language and the microblogging platform Twitter, investigating methods for extracting emotion of individual tweets as well as population emotion for different subjects (hashtags). Design/methodology/approach The authors propose and investigate the use of emotion lexicon-based methods as a mean of extracting emotion/sentiment information from social media. We compare several approaches for measuring the intensity of six emotions: anger, disgust, fear, happiness, sadness, and surprise. To evaluate the effectiveness of our methods, we develop a benchmark dataset of tweets, manually rated by two humans Findings Development of a new sentiment lexicon for use in web applications. We then assess the performance of our methods with the new lexicon and find improved results. Research limitations/implications Automated emotion results of research seem promising and correlate to real user emotion. At this point the authors make some interesting observations about the lexicon-based approach which lead to the need for a new, better, emotion lexicon Practical implications The authors examine the variation of emotion intensity over time for selected hashtags, and associate it with real-world events. Originality/value The originality in this research is the development of a training set of tweets, manually annotated by two independent raters. We `transfer' the sentiment information of these annotated tweets, in a meaningful way, to the set of words that appear in them. }
    }

  • Mallis, D., Sgouros, T. & Mitianoudis, N. (2017) Convolutive audio source separation using robust ica and an intelligent evolving permutation ambiguity solution. IN Evolving systems, .. doi:10.1007/s12530-017-9199-3
    [BibTeX] [Abstract] [Download PDF]

    Audio source separation is the task of isolating sound sources that are active simultaneously in a room captured by a set of microphones. Convolutive audio source separation of equal number of sources and microphones has a number of shortcomings including the complexity of frequency-domain ICA, the permutation ambiguity and the problem’s scalabity with increasing number of sensors. In this paper, the authors propose a multiple-microphone audio source separation algorithm based on a previous work of Mitianoudis and Davies [IEEE Trans Speech Audio Process 11(5):489–497, 2003]. Complex FastICA is substituted by Robust ICA increasing robustness and performance. Permutation ambiguity is solved using two methodologies. The first is using the Likelihood Ration Jump solution, which is now modified to decrease computational complexity in the case of multiple microphones. The application of the MuSIC algorithm, as a preprocessing step to the previous solution, forms a second methodology with promising results.

    @Article{Mallis2017,
    author="Mallis, Dimitrios
    and Sgouros, Thomas
    and Mitianoudis, Nikolaos",
    title="Convolutive audio source separation using robust ICA and an intelligent evolving permutation ambiguity solution",
    journal="Evolving Systems",
    year="2017",
    month="Jul",
    day="29",
    abstract="Audio source separation is the task of isolating sound sources that are active simultaneously in a room captured by a set of microphones. Convolutive audio source separation of equal number of sources and microphones has a number of shortcomings including the complexity of frequency-domain ICA, the permutation ambiguity and the problem's scalabity with increasing number of sensors. In this paper, the authors propose a multiple-microphone audio source separation algorithm based on a previous work of Mitianoudis and Davies [IEEE Trans Speech Audio Process 11(5):489--497, 2003]. Complex FastICA is substituted by Robust ICA increasing robustness and performance. Permutation ambiguity is solved using two methodologies. The first is using the Likelihood Ration Jump solution, which is now modified to decrease computational complexity in the case of multiple microphones. The application of the MuSIC algorithm, as a preprocessing step to the previous solution, forms a second methodology with promising results.",
    issn="1868-6486",
    doi="10.1007/s12530-017-9199-3",
    url="http://www.dimitrismallis.eu/wp-content/uploads/2018/04/EvolvingSystem.pdf"
    }

  • Mallis, D., Sgouros, T. & Mitianoudis, N. (2016) Convolutive audio source separation using robust ica and reduced likelihood ratio jump IN Iliadis, L. & Maglogiannis, I. (Eds.), . Cham, Springer International Publishing, 230–241.
    [BibTeX] [Abstract] [Download PDF]

    Audio source separation is the task of isolating sound sources that are active simultaneously in a room captured by a set of microphones. Convolutive audio source separation of equal number of sources and microphones has a number of shortcomings including the complexity of frequency-domain ICA, the permutation ambiguity and the problem’s scalabity with increasing number of sensors. In this paper, the authors propose a multiple-microphone audio source separation algorithm based on a previous work of Mitianoudis and Davies [1]. Complex FastICA is substituted by Robust ICA increasing robustness and performance. Permutation ambiguity is solved using the Likelihood Ration Jump solution, which is now modified to decrease computational complexity in the case of multiple microphones.

    @InProceedings{10.1007/978-3-319-44944-9_20,
    author="Mallis, Dimitrios
    and Sgouros, Thomas
    and Mitianoudis, Nikolaos",
    editor="Iliadis, Lazaros
    and Maglogiannis, Ilias",
    title="Convolutive Audio Source Separation Using Robust ICA and Reduced Likelihood Ratio Jump",
    booktitle="Artificial Intelligence Applications and Innovations",
    year="2016",
    publisher="Springer International Publishing",
    address="Cham",
    pages="230--241",
    abstract="Audio source separation is the task of isolating sound sources that are active simultaneously in a room captured by a set of microphones. Convolutive audio source separation of equal number of sources and microphones has a number of shortcomings including the complexity of frequency-domain ICA, the permutation ambiguity and the problem's scalabity with increasing number of sensors. In this paper, the authors propose a multiple-microphone audio source separation algorithm based on a previous work of Mitianoudis and Davies [1]. Complex FastICA is substituted by Robust ICA increasing robustness and performance. Permutation ambiguity is solved using the Likelihood Ration Jump solution, which is now modified to decrease computational complexity in the case of multiple microphones.",
    isbn="978-3-319-44944-9",
    url="http://www.dimitrismallis.eu/wp-content/uploads/2018/04/aiai2016.pdf"
    }

  • Kalamatianos, G., Mallis, D., Symeonidis, S. & Arampatzis, A. (2015) Sentiment analysis of greek tweets and hashtags using a sentiment lexicon New York, NY, USA, ACM, 63–68. doi:10.1145/2801948.2802010
    [BibTeX] [Abstract] [Download PDF]

    The rapid growth of social media has rendered opinion and sentiment mining an important area of research with a wide range of applications. We focus on the Greek language and the microblogging platform “Twitter”, investigating methods for extracting sentiment of individual tweets as well population sentiment for different subjects (hashtags). The proposed methods are based on a sentiment lexicon. We compare several approaches for measuring the intensity of “Anger”, “Disgust”, “Fear”, “Happiness”, “Sadness”, and “Surprise”. To evaluate the effectiveness of our methods, we develop a benchmark dataset of tweets, manually rated by two humans. Our automated sentiment results seem promising and correlate to real user sentiment. Finally, we examine the variation of sentiment intensity over time for selected hashtags, and associate it with real-world events.

    @inproceedings{Kalamatianos:2015:SAG:2801948.2802010,
    author = {Kalamatianos, Georgios and Mallis, Dimitrios and Symeonidis, Symeon and Arampatzis, Avi},
    title = {Sentiment Analysis of Greek Tweets and Hashtags Using a Sentiment Lexicon},
    booktitle = {Proceedings of the 19th Panhellenic Conference on Informatics},
    series = {PCI '15},
    year = {2015},
    isbn = {978-1-4503-3551-5},
    location = {Athens, Greece},
    pages = {63--68},
    numpages = {6},
    url = {http://www.dimitrismallis.eu/wp-content/uploads/2018/04/PCI2015a.pdf},
    doi = {10.1145/2801948.2802010},
    acmid = {2802010},
    publisher = {ACM},
    address = {New York, NY, USA},
    keywords = {sentiment lexicon, sentiment mining, social media, twitter},
    abstract="The rapid growth of social media has rendered opinion and
    sentiment mining an important area of research with a wide range
    of applications. We focus on the Greek language and the
    microblogging platform “Twitter”, investigating methods for
    extracting sentiment of individual tweets as well population
    sentiment for different subjects (hashtags). The proposed methods
    are based on a sentiment lexicon. We compare several approaches
    for measuring the intensity of “Anger”, “Disgust”, “Fear”,
    “Happiness”, “Sadness”, and “Surprise”. To evaluate the
    effectiveness of our methods, we develop a benchmark dataset of
    tweets, manually rated by two humans. Our automated sentiment
    results seem promising and correlate to real user sentiment. Finally,
    we examine the variation of sentiment intensity over time for
    selected hashtags, and associate it with real-world events."
    }