-

! 5 14-07-00682 !! "

! % ! & ! ! / ! " '& ": ! . 0

%*: 1 '! %. 2 ! '! 1 '! ! %.

1 ! ) ! * 44 * ! *#" '!#" .

* 6 '&

) $ ) *! ! %

! ! ! # ", ! ) "

# % ! * , 1

. ) ! & ) # ! ! - * 2 1 $/ * + * ' *, '!

# #* !!#+ 500 * ! % !

'& $ % # 1 ! % . ! * )

* ! % + %/ + ! * - # © . .

! ! " ) # # %/ !!#+ ! ! ! ! '! [e-mail] * ! ! / ! ".

) + ) ! & ', !

* ! - & * ! . 2 '!#+

- ! , *

«& ! !) #* * . % ! % 2 #

'!#+ / ! " , " ! & 1 ! ", ! 3 *

". 3 * , ! * #+ ». 9&# * , * ! '! 1 ' ! ) «& !

% / ! %* , ! ! / ! " [2, 10, 15, ! % % % ) **!#+ + * + !

! & ! ! % * [ 14, 18 ]. 2 , !- ! CLEF * '!#+ ",

& !!#+ 2012– 2014 + ! ! 2 [ 3-4 ]. 2014-2015 ) ! & ! ! ! & ! '!

* %&# SentiRuEval [ 11 ]. ! * & & SentiRuEval # ! * ! ! & ! # '! * ) ! & " * &

, + !# + + # ! & .

!! " !!# , & ' - , * / $/ + '% $/ * !!#+ ) ! & &

! ! '! !! " ) ! & !

! " . 2

! *#

" & ' ! " + $/ * !

& & & ",

. 6 $ ! %. ! ! ! "

& !!#+ ' *# ! # , & & *.

!

# ! '! & ' ! !# 1 . 6

'& &# ! %* ,

"

XVII DAMDID/RCDL’2015 « ! ' », !

* *! 1 ' #+ », & * '! % & ! * $ % * 1 ) '! 22]. ; % '& 3 , ! ' 2 &# $ !!#+ ! %! , & * SentiRuEval,

! . !#+ 1! / ! " 2 !- ! & ! ) &

* ! '! .

: - % / ! %.

', % % ! ! "

' / ! &

! #% !- * [ 14, 18 ].

2012–2014 ) +, * + !- ! CLEF, + ! ! * ! (online reputation management systems) RepLab [ 3-4 ]. ' ! ! % % *, # ', 1 '! ', , ! 52,42 32,3 22,1 *# ! '!

#+ !! " *#

!!#+. * * $/ * $/ " + 1 2.

! ' ! " / ! " * 1

'!#* ! "

#, & ! ! )

! !#+ !#+ '& ! *

! " * ! .

* ! % 4,12% % $/ " !!#+ * ! " * ) % '

% !

' ", 3 * ** ! . 6 '&

, $ , * ) * ! * 1 * ! " & , ! $ %. ! ) '& ! + %

%$ 1 '!# #, &! $/ 3* !

! ) !# ! !# * : «@VadimSavin ! ... *! " * - ! ! ))».

#, ! ! # ! & ' ,

! # & * , & ' % ) !# ( * % !

#* '* ) / ! %.

*

$/ !# ! 20 000 1 $ $/ "

! 3*

' 6 3 * & $ + 3.2 $ ! ! ! ! &* &* &* ! '! 6 3 * , 1 % # * , 3* ! ! 3 # %

# * . / "

/ ! " , * ! $

". A 1 % * ! * * & &* / ! % '! / ! ! & ' #&# $ ) , 1!

# 1! # 10 000 / ! " ' % "

% # *% * .

#% ! ', *! ! % * # ' ! ! .

% ! ' % # ! !

* ! ! #

!!# * !%$ , !

) " % , *% " ! # macro , ) F – F-measure F – F-measure % measure % - * 2. ! '! ) '! )

# 1 ) ! .

2 P F

R '! ! * - !

# . 4 ! % & & ' !#

4. 2 &* % ! $ 2 ) .

* !! ) : n -) **#

n-) **# , ! !

! !! ) ! ! 1 " % PMI & ! * !

& # !

& '

# $ %.

!# % '! /!

", " " ! 5), & # ' 1

% * MacroF). A

** ! &! '! ; % !

$/ " * ! " % !

#+ !

" % ! &# '! " ) ! ' % ! ! " # * ! * * # $/ " $ % ! 1. 2 ' '

1. & ', !

!!#+ ! & ' * * '!# )! #

! & ** ! !!#+ * ! %+ &! $ % (0,36 vs. 0,488 MacroF). V

! (% ! ! & %* !! + ! ) ! ) / !! " &! * 1! & ' ! + # '!

! * 1 , DKL i

testi ln 1 ( traini ln traini ), (6) 2 i M 2 1 *# ! ! % * $ *

# DJS 1

( testi ln 2 i U ! 2AA U ! 2AA 2 6 &! ( ) ! ! '

1.2) !# ! ) * , % %$ % !#

& $/ " ! !#*, ! !# ! , . V

, # # 1 $ *# $/ " # !!

+ '!#* )! %

" , ! %* , %&

*, ! 3 $ !# ' NRC Word-Emotion ' #&# $ $ " ; % !) " # *%! #" Association lexicon, $/ 3* # ' %&# & *

.

(' 2

'% ! ) + ! ! ! %! $ % *! ! %, !

* ,

#. * $

, !# , & * !" / / , # ! , ! ! $ ! *

) & ! '! /! ', . ; % 3 ) * ! + % – %

'. !

* ! $ % 9 ! , # * !! )

% !#* # & ' " !

, $/ * &

! " % % $/ "

$ " %/ + & '

% $/ " '!#" ' % ! % ' +

This paper summarizes the results of the reputationoriented Twitter task, which was held as a part of SentiRuEval evaluation of Russian sentiment-analysis systems. The tweets in two domains: telecom companies and banks – were included in the evaluation. The task was to determine if an author of a tweet has a positive or negative attitude to a company mentioned in the message. The main issue of this paper is to analyze the current state and problems of approaches applied by the participants.

References

[1] Adaskina Yu . V., Panicheva P. V. , Popov A. M. Syntax-based Sentiment Analysis of Tweets in Russian / / In Proceedings of International Conference Dialog. - 2015 . - 2 . 2. - . 25 - 35 .

[2] Agarwal A. , Xie B. , Vovsha I. , Rambow O. , Passonneau , R. Sentiment analysis of twitter data // Proceedings of the Workshop on Languages in Social Media. - Association for Computational Linguistics , 2011 . - . 30 - 38 .

[3] Amigo E. , Corujo A. , Gonzalo J. , Meij E., de Rijke M. Overview of RepLab 2012: Evaluating Online Reputation Management Systems // CLEF 2012 Evaluation Labs and Workshop Notebook Papers. - 2012.

[4] Amigo E. , Albornoz J.C. , Chugur I. , Corujo A. , Gonzalo J. , Martin T. , Meij E ., de Rijke M , Spina D . Overview of RepLab 2013: Evaluating online reputation monitoring systems //Information Access Evaluation . Multilinguality, Multimodality, and Visualization . - Springer Berlin Heidelberg, 2013 . - . 333 - 352 .

[5] Chetviorkin I. , Braslavskiy P. , Loukachevich N. Sentiment analysis track at romip 2011 //Dialog. - 2012 .

[6] Chetviorkin I. , Loukachevitch N. V. Extraction of Russian Sentiment Lexicon for Product MetaDomain / /COLING. - 2012 . - . 593 - 610 .

[7] Chen S. F. , Goodman J. An empirical study of smoothing techniques for language modeling //Proceedings of the 34th annual meeting on Association for Computational Linguistics . - Association for Computational Linguistics, 1996 . - . 310 - 318 .

[8] Feng , S. , Kang , J.S. , Kuznetsova , P. , Choi , Y. : Connotation Lexicon: A Dash of Sentiment Beneath the Surface Meaning / /ACL (1). - 2013 . - . 1774 - 1784 .

[9] Hogenboom , A. , Bal , D. , Frasincar , F. , Bal , M., de Jong, F., & Kaymak , U. Exploiting emoticons in sentiment analysis // Proceedings of the 28th Annual ACM Symposium on Applied Computing. - ACM , 2013 . - . 703 - 710 .

[10] Kouloumpis E. , Wilson T., Moore J . Twitter sentiment analysis: The good the bad and the omg ! //ICWSM. - 2011 . - 2 . 11 . - . 538 - 541 .

[11] Loukachevitch , N. , Blinov , P. , Kotelnikov , E. , Rubtsova Yu , V. , Ivanov , V. V. , Tutubalina , E. SentiRuEval: testing object-oriented sentiment analysis systems in Russian . // In Proceedings of International Conference Dialog. - 2015 . - 2 . 2. - . 12 - 24 .

[12] Mohammad S. M. , Kiritchenko S. , Zhu X. NRCCanada: Building the state-of-the-art in sentiment analysis of tweets // Proceedings of the Second Joint Conference on Lexical and Computational Semantics (SEMSTAR'13) . - 2013.

[13] Mohammad S. M. , Turney P. D. Crowdsourcing a word-emotion association lexicon //Computational Intelligence. - 2013 . - 2 . 29 . - 5 . 3. - . 436 - 465 .

[14] Nakov P. et al. Semeval -2013 task 2: Sentiment analysis in twitter // Proceedings of the 7th International Workshop on Semantic Evaluation (SemEval-2013) , - 2013 . - . 312 - 320 .

[15] Pak A. , Paroubek P . Twitter as a Corpus for Sentiment Analysis and Opinion Mining //LREC. - 2010 . - 2 . 10 . - . 1320 - 1326 .

[16] Polyakov P. Yu. , Kalinina M. V. , Pleshko V. V. , Automatic Object-oriented Sentiment Analysis by Means of Semantic Templates and Sentiment Lexicon Dictionaries // In Proceedings of International Conference Dialog. - 2015 . - 2 . 2. - . 68 - 76 .

[17] Read J. Using emoticons to reduce dependency in machine learning techniques for sentiment classification // Proceedings of the ACL Student Research Workshop . - Association for Computational Linguistics, 2005 . - . 43 - 48 .

[18] Rosenthal S. , Ritter A. , Nakov P. , Stoyanov V . SemEval-2014 Task 9: Sentiment Analysis in Twitter // Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014 ). - 2014 . - . 73 - 80 .

[19] Tutubalina E. V. , Zagulova M. A. , Ivanov V. V. , Malykh V. A. , A Supervised Approach for SentiRuEval Task on Sentiment Analysis of Tweets about Telecom and Financial Companies // In Proceedings of International Conference Dialog. - 2015 . - 2 . 2. - . 89 - 99 .

[20] Vasilyev V. G. , Denisenko A. A. , Solovyev D. A. , Aspect Extraction and Twitter Sentiment Classification by Fragment Rules / / In Proceedings of International Conference Dialog. - 2015 . - 2 . 2. - . 100 - 110 .

[21] Wilson T. , Wiebe J. , Hoffmann P. Recognizing contextual polarity in phrase-level sentiment analysis //Proceedings of the conference on human language technology and empirical methods in natural language processing . - Association for Computational Linguistics, 2005 . - . 347 - 354 .