Five-Dimensional Sentiment Analysis of Corpora, Documents and Words

Timo Honkela*, Jaakko Korhonen, Krista Lagus, Esa Saarinen

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

4 Sitaatiot (Scopus)
249 Lataukset (Pure)

Abstrakti

Sentiment analysis has become a widely used approach to assess the emotional content of written documents such as customer feedback. In positive psychology research, the typical one-dimensional analysis framework has been extended to include five dimensions. This five-dimensional model, PERMA, enables a fine-grained analysis of written texts. We propose an approach in which this model, statistical analysis and the self-organizing map are used. We analyze corpora from various genres. A hybrid methodology that uses the self-organizing maps algorithm and human judgment is suggested for expanding the PERMA lexicon. This vocabulary expansion can be useful for English but it is potentially even more crucial in the case of other languages for which the lexicon is not readily available. The challenges and solutions related to the text mining of texts written in a morphologically complex language such as Finnish are also considered.

AlkuperäiskieliEnglanti
OtsikkoAdvances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 10th International Workshop, WSOM 2014
KustantajaSpringer Verlag
Sivut209-218
Sivumäärä10
ISBN (painettu)9783319076942
DOI - pysyväislinkit
TilaJulkaistu - 2014
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaINTERNATIONAL WORKSHOP ON SELF-ORGANIZING MAPS - Mittweida, Saksa
Kesto: 2 heinäk. 20144 heinäk. 2014
Konferenssinumero: 10

Julkaisusarja

NimiAdvances in Intelligent Systems and Computing
Vuosikerta295
ISSN (painettu)21945357

Workshop

WorkshopINTERNATIONAL WORKSHOP ON SELF-ORGANIZING MAPS
LyhennettäWSOM
Maa/AlueSaksa
KaupunkiMittweida
Ajanjakso02/07/201404/07/2014

Sormenjälki

Sukella tutkimusaiheisiin 'Five-Dimensional Sentiment Analysis of Corpora, Documents and Words'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä