izpis_h1_title_alt

Napovedovanje čustvene naravnanosti avtorjev v spletnih komentarjih : diplomsko delo
Kosec, Urška (Author), Zupan, Blaž (Mentor) More about this mentor... This link opens in a new window

URLURL - Presentation file, Visit http://eprints.fri.uni-lj.si/2568/ This link opens in a new window

Abstract
V nalogi smo raziskali napovedljivost sentimentalnega pridiha avtorjev v komentarjih spletnih novic. Na področju tovrstne analize besedil je bilo v preteklih letih objavljeno večje število sorodnih raziskav za angleški jezik, a ker za slovenščino, razen v nedavni diplomski nalogi na UL FRI, podobnih raziskav nismo zasledili, je to glede na vse posebnosti slovenskega jezika za našo nalogo predstavljalo še dodatni izziv. Kratka besedila smo želeli čimbolj točno razvrstiti v kategoriji pozitivnih oziroma negativnih komentarjev. Preučili smo, kako se ta problem razlikuje od klasičnega razvrščanja besedil glede na temo. V nalogi ugotovimo, da uporabljene tehnike strojnega učenje ne dosegajo pričakovanih rezultatov. Možen razlog za takšno odstopanje je predstavitev besedil z n-terkami znakov, ki ne upošteva semantike besedila oziroma besed, iz katerih je komentar sestavljen, ter ne upošteva njihovih morebitnih interakcij. Dodatna težavnost pri nalogi so tudi zelo kratki komentarji.

Language:Slovenian
Keywords:napovedovanje čustvene naravnanosti, rudarjenje mnenj, odkrivanje znanj iz podatkov, strojno učenje, n-terka, klasifikacijske metode, logloss, ocena točnosti, logistična regresija, metoda podpornih vektorjev, metoda k najbližjih sosedov, metoda naključnih gozdov, skladanje, računalništvo, univerzitetni študij, diplomske naloge
Work type:Undergraduate thesis (m5)
Tipology:2.11 - Undergraduate Thesis
Organization:FRI - Faculty of computer and information science
Year:2014
Publisher:[U. Kosec]
Number of pages:90 str.
UDC:004(043.2)
COBISS.SI-ID:10634324 Link is opened in a new window
Views:576
Downloads:128
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:English
Title:Sentiment prediction for comments of web news articles
Abstract:
The Thesis dealt with machine learning-based classification of the sentimental impact of the comments posted with news articles on the web. In the past years sentiment analysis has become an important research topics with substantial number of publications for texts in English, while for the Slovene, except in the recent thesis at the University of Ljubljana, Faculty of Computer and Information science, the topic has not been explored well. In relation to all the features of the Slovenian language this represented an additional challenge. Our goal was to correctly classify these comments as positive or negative. We examined how this problem differs from the topical classification of texts. Our work shows that the problem is hard and that a typical application of machine learning based on k-mer representation of text does not yield the expected results. A possible reason for poor performance may be lack of semantic information in such representation and short length of the texts.

Keywords:sentiment prediction, opinion mining, data mining, machine learning, k-mer, classification methods, logloss, accuracy score, logistic regression, support vector machines, k-nearest neighbours, random forests, stacking, computer science, diploma

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back