=Paper=
{{Paper
|id=Vol-1110/paper1
|storemode=property
|title=Domain-Based Lexicon Enhancement for Sentiment Analysis
|pdfUrl=https://ceur-ws.org/Vol-1110/paper1.pdf
|volume=Vol-1110
|dblpUrl=https://dblp.org/rec/conf/sgai/MuhammadWLG13a
}}
==Domain-Based Lexicon Enhancement for Sentiment Analysis==
https://ceur-ws.org/Vol-1110/paper1.pdf
Domain-Based Lexicon Enhancement
for Sentiment Analysis
Aminu Muhammad, Nirmalie Wiratunga, Robert Lothian and Richard Glassey
IDEAS Research Institute, Robert Gordon University, Aberdeen UK
{a.b.muhammad1, n.wiratunga, r.m.lothian, r.j.glassey}@rgu.ac.uk
Abstract. General knowledge sentiment lexicons have the advantage of wider
term coverage. However, such lexicons typically have inferior performance for
sentiment classification compared to using domain focused lexicons or machine
learning classifiers. Such poor performance can be attributed to the fact that some
domain-specific sentiment-bearing terms may not be available from a general
knowledge lexicon. Similarly, there is difference in usage of the same term be-
tween domain and general knowledge lexicons in some cases. In this paper, we
propose a technique that uses distant-supervision to learn a domain focused sen-
timent lexicon. The technique further combines general knowledge lexicon with
the domain focused lexicon for sentiment analysis. Implementation and eval-
uation of the technique on Twitter text show that sentiment analysis benefits
from the combination of the two knowledge sources. The technique also per-
forms better than state-of-the-art machine learning classifiers trained with distant-
supervision dataset.
1 Introduction
Sentiment analysis concerns the study of opinions expressed in text. Typically, an opin-
ion comprises of its polarity (positive or negative), the target (and aspects) to which the
opinion was expressed and the time at which the opinion was expressed [14]. Sentiment
analysis has a wide range of applications for businesses, organisations, governments
and individuals. For instance, a business would want to know customer’s opinion about
its products/services and that of its competitors. Likewise, governments would want to
know how their policies and decisions are received by the people. Similarly, individuals
would want make use of other people’s opinion (reviews or comments) to make deci-
sions [14]. Also, applications of sentiment analysis have been established in the areas
of politics [3], stock markets [1], economic systems [15] and security concerns [13]
among others.
Typically, sentiment analysis is performed using machine learning or lexicon-based
methods; or a combination of the two (hybrid). With machine learning, an algorithm is
trained with sentiment labelled data and the learnt model is used to classify new docu-
ments. This method requires labelled data typically generated through labour-intensive
human annotation. An alternative approach to generating labelled data called distant-
supervision has been proposed [9, 23]. This approach relies on the appearance of cer-
tain emoticons that are deemed to signify positive (or negative) sentiment to tentatively
labelled documents as positive (or negative). Although, training data generated through
7
distant-supervision have been shown to do well in sentiment classification [9], it is hard
to integrate into a machine learning algorithm, knowledge which is not available from
its training data. Similarly, it is hard to explain the actual evidence on which a machine
learning algorithm based its decision.
The lexicon-based, on the other hand, involves the extraction and aggregation of
terms’ sentiment scores offered by a lexicon (i.e prior polarities) to make sentiment
prediction. Sentiment lexicons are language resources that associate terms with senti-
ment polarity (positive, negative or neutral) usually by means of numerical score that
indicate sentiment dimension and strength. Although sentiment lexicon is necessary for
lexicon-based sentiment analysis, it is far from enough to achieve good results [14].
This is because the polarity with which a sentiment-bearing term appears in text (i.e.
contextual polarity) could be different from its prior polarity. For example in the text
“the movie sucks”, although the term ’sucks’ seems highly sentiment-bearing, this may
not be reflected by a sentiment lexicon. Another problem with sentiment lexicons is that
they do not contain domain-specific, sentiment-bearing terms. This is especially more
common when a lexicon generated from standard formal text is applied in sentiment
analysis of informal text.
In this paper, we introduce lexicon enhancement technique (LET) to address the
the afore-mentioned problems of lexicon-based sentiment analysis. LET leverages the
success of distant-supervision to mine sentiment knowledge from a target domain and
further combines such knowledge with the one obtained from a generic lexicon. Eval-
uation of the technique on sentiment classification of Twitter text shows performance
gain over using either of the knowledge sources in isolation. Similarly, the techniques
performs better than three standard machine learning algorithms namely Support Vec-
tor Machine, Naive Bayes and Logistic Regression. The main contribution of this paper
is two-fold. First, we introduce a new fully automated approach of generating social
media focused sentiment lexicon. Second, we propose a strategy to effectively combine
the developed lexicon with a general knowledge lexicon for sentiment classification.
The remainder of this paper is organised as follows. Section 2 describes related
work. The proposed technique is presented in Section 3. Evaluation and discussions
appear in Section 4, followed by conclusions and future work in Section 5.
2 Related Work
Typically, three methods have been employed for sentiment analysis namely machine
learning, lexicon based and hybrid. For machine learning, supervised classifiers are
trained with sentiment labelled data commonly generated through labour-intensive hu-
man annotation. The trained classifiers are then used to classify new documents for sen-
timent. Prior work using machine learning include the work of Pang et al [20], where
three classifiers namely, Naı̈ve Bayes (NB), Maximum Entropy (ME) and Support Vec-
tor Machines (SVMs) were used for the task. Their results show that, like topic-based
text classification, SVMs perform better than NB and ME. However, performance of
all the three classifiers in sentiment classification is lower than in topic-based text clas-
sification. Document representation for machine learning is an unordered list of terms
that appear in the documents (i.e. bag-of-words). A binary representation based on term
8
presence or absence attained up to 87.2% accuracy on a movie review dataset [18].
The addition of phrases that are used to express sentiment (i.e. appraisal groups) as ad-
ditional features in the binary representation resulted in further improvement of 90.6%
[32] while best result of 96.9% was achieved using term-frequency/inverse-document-
frequency (tf/idf) weighting [19]. Further sentiment analysis research using machine
learning attempt to improve classification accuracy with feature selection mechanisms.
An approach for selecting bi-gram features was introduced in [16]. Similarly, feature
space reduction based on subsumption hierarchy was introduced in [24]. The afore-
mentioned works concentrate on sentiment analysis of reviews, therefore, they used
star-rating supplied with reviews to label training and test data instead of hand-labelling.
This is typical with reviews, however, with other forms of social media (e.g. discussion
forums, blogs, tweets e.t.c.), star-rating is typically unavailable. Distant-supervision has
been employed to generate training data for sentiment classification of tweets [9, 23].
Here, emoticons supplied by authors of the tweets were used as noisy sentiment la-
bels. Evaluation results on NB, ME and SVMs trained with distant-supervision data
but tested on hand-labelled data show the approach to be effective with ME attaining
the highest accuracy of 83.0% on a combination of unigram and bigram features. The
limitation of machine learning for sentiment analysis is that it is difficult to integrate
into a classifier, general knowledge which may not be acquired from training data. Fur-
thermore, learnt models often have poor adaptability between domains or different text
genres because they often rely on domain specific features from their training data.
Also, with the dynamic nature of social media, language evolves rapidly which may
render a previous learning less useful.
The lexicon based method excludes the need for labelled training data but requires
sentiment lexicon which several are readily available. Sentiment lexicons are dictionar-
ies that associate terms with sentiment values. Such lexicons are either manually gener-
ated or semi-automatically generated from generic knowledge sources. With manually
generated lexicons such as General Inquirer [25] and Opinion Lexicon [12], sentiment
polarity values are assigned purely by humans and typically have limited coverage. As
for the semi-automatically generated lexicons, two methods are common, corpus-based
and dictionary-based. Both methods begin with a small set of seed terms. For example,
a positive seed set such as ‘good’, ‘nice’ and ‘excellent’ and a negative seed set could
contain terms such as ‘bad’, ‘awful’ and ‘horrible’. The methods leverage on language
resources and exploit relationships between terms to expand the sets. The two methods
differ in that corpus-based uses collection of documents while the dictionary-based uses
machine-readable dictionaries as the lexical resource. Corpus-based was used to gen-
erate sentiment lexicon [11]. Here, 657 and 679 adjectives were manually annotated
as positive and negative seed sets respectively. Thereafter, the sets were expanded to
conjoining adjectives in a document collection based on the connectives ‘and’ and ‘but’
where ‘and’ indicates similar and ‘but’ indicates contrasting polarities between the con-
joining adjectives. Similarly, a sentiment lexicon for phrases generated using the web as
a corpus was introduced in [29, 30]. Dictionary-based was used to generate sentiment
lexicon in [2, 31]. Here, relationships between terms in WordNet [8] were explored
to expand positive and negative seed sets. Both corpus-based and dictionary-based lex-
9
icons seem to rely on standard spelling and/or grammar which are often not preserved
in social media [27].
Lexicon-based sentiment analysis begins with the creation of a sentiment lexicon or
the adoption of an existing one, from which sentiment scores of terms are extracted and
aggregated to predict sentiment of a given piece of text. Term-counting approach has
been employed for the aggregation. Here, terms contained in the text to be classified
are categorised as positive or negative and the text is classified as the class with highest
number of terms [30]. This approach does not account for varying sentiment intensities
between terms. An alternative approach is the aggregate-and-average strategy [26].
This classifies a piece of text as the class with highest average sentiment of terms. As
lexicon-based sentiment analysis often rely on generic knowledge sources, it tends to
perform poorly compared to machine learning.
Hybrid method, in which some elements from machine learning and lexicon based
are combined, has been used in sentiment analysis. For instance, sentiment polarities
of terms obtained from lexicon were used as additional features to train machine learn-
ing classifiers [5, 17]. Similarly, improvement was observed when multiple classifiers
formed from different methods are used to classify a document [22]. Also, machine
learning was employed to optimize ݂ݐሺݏݐ݊݁݉ݑܿ݀݁ݒ݅ݐܽ݃݁݊ א ݐሻ
ߙ ൬ sentiment scores in a lexicon [28]. Here,
൰ ሺͳ initial
െ ߙሻ݈݁݁ݎܿܵ݁ݒ݅ݏܲ݊ܿ݅ݔሺݐሻ
݂ݐሺݏݐ݊݁݉ݑܿ݀݁ݒ݅ݐܽ݃݁݊ ݁ݒ݅ݐ݅ݏ א ݐሻ
݊݁݃ܽ݁ݎܿܵ݁ݒ݅ݐሺݐሻ
score for terms, ൌ
assigned manually are increased or decreased based on observed clas-
ʹ
sification accuracies.
3 Lexicon Enhancement Technique
Lexicon enhancement technique (LET) addresses the semantic gap between generic
and domain knowledge sources. As illustrated in Fig. 1, the technique involves ob-
taining scores from a generic lexicon, automated domain data labelling using distant-
supervision, domain lexicon generation and aggregation strategy for classification. De-
tails of these components is presented in the following sub sections.
-,/
Datalabelling Domain
Unlabelled usingdistantͲ lexicon
data supervision generation
Aggregation
Generic forsentiment
Lexicon classification
Fig. 1. Diagram showing the architectural components of the proposed technique (LET)
10
3.1 Generic Lexicon
We use SentiWordNet [7] as the source of generic sentiment scores for terms. Senti-
WordNet is a general knowledge lexicon generated from WordNet [8]. Each synset (i.e.
a group of synonymous terms based on meaning) in WordNet is associated with three
numerical scores indicating the degree of association of the synset with positive, neg-
ative and objective text. In generating the lexicon, seed (positive and negative) synsets
were expanded by exploiting synonymy and antonymy relations in WordNet, whereby
synonymy preserves while antonymy reverses the polarity with a given synset. As there
is no direct synonym relation between synsets in WordNet, the relations: see also, simi-
lar to, pertains to, derived from and attribute were used to represent synonymy relation
while direct antonym relation was used for the antonymy. Glosses (i.e. textual defi-
nitions) of the expanded sets of synsets along with that of another set assumed to be
composed of objective synsets were used to train eight ternary classifiers. The clas-
sifiers are used to classify every synset and the proportion of classification for each
class (positive, negative and objective) were deemed as initial scores for the synsets.
The scores were optimised by a random walk using the PageRank [4] approach. This
starts with manually selected synsets and then propagates sentiment polarity (positive
or negative) to a target synset by assessing the synsets that connect to the target synset
through the appearance of their terms in the gloss of the target synset. SentiWordNet
can be seen to have a tree structure as shown in Fig. 2. The root node of the tree is a
term whose child nodes are the four basic PoS tags in WordNet (i.e. noun, verb, adjec-
tive and adverb). Each PoS can have multiple word senses as child nodes. Sentiment
scores illustrated by a point within the triangular space in the diagram are attached to
word-senses. Subjectivity increases (while objectivity decreases) from lower to upper,
and positivity increases (while negativity decreases) from right to the left part of the
triangle.
We extract scores from SentiWordNet as follows. First, input text is broken into unit
tokens (tokenization) and each token is assigned a lemma (i.e. corresponding dictionary
entry) and PoS using Stanford CoreNLP library1 . Although in SentiWordNet scores are
associated with word-senses, disambiguation is usually not performed as it does not
seem to yield better results than using either the average score across all senses of a
term-PoS or the score attached to the most frequent sense of the term (e.g. in [21], [17],
[6]). In this work, we use average positive (or negative) score at PoS level as the positive
(or negative) for terms as shown in Equation 1.
|senses(t,PoS)|
∑ ScoreSensei (t, PoS)dim
i=1
gs(t)dim = (1)
|senses(t, PoS)|
Where gs(t)dim is the score of term t (given its part-of-speech, PoS) in the sentiment
dimension of dim (dim is either positive or negative). ScoreSensei (t, PoS)dim is the sen-
timent score of the term t for the part-of-speech (PoS) at sense i. Finally, |senses(t, PoS)|
is number of word senses for the part-of-speech (PoS) of term t.
1 nlp.stanford.edu/software/corenlp.shtml
11
Term
Noun Verb Adjective Adverb
s1 sn1 s1 sn2 s1 sn3 s1 sn4
Fig. 2. Diagram showing the structure of SentiWordNet
3.2 Data Labelling Using Distant-Supervision
Distant-supervision offers an automated approach to assigning sentiment class labels to
documents. It uses emoticons as noisy labels for documents. It is imperative to have as
many data as possible at this stage as this affects the reliability of scores to be gener-
ated at the subsequent stage. Considering that our domain of focus is social media, we
assume there will be many documents containing such emoticons and, therefore, large
dataset can be formed using the approach. Specifically, in this work we use Twitter as
a case study. We use a publicly available distant-supervision dataset for this stage [9]2 .
This dataset contains 1,600,000 tweets balanced for positive and negative sentiment
classes. We selected first 10,000 tweets from each class for this work. This is because
the full dataset is too big to conveniently work with. For instance, building a single
machine learning model on the full dataset took several days on a machine with 8GB
RAM, 3.2GHZ Processor and 64bit Operating System. However, we aim to employ ”big
data” handling techniques to experiment with larger datasets in the future. The dataset
is preprocessed to reduce feature space using the approach introduced in [9]. That is,
all user names (i.e. words that starts with the @ symbol) are replaced with the token
‘USERNAME’. Similarly all URLs (e.g. “http://tinyurl.com/cvvg9a”) are replaced with
the token ‘URL’. Finally, words consisting of sequence of three or more repeated char-
acter (e.g. ”haaaaapy”) are normalised to contain only two of such repeated character
in sequence.
2 The dataset available from Sentiment140.com
12
3.3 Domain Lexicon Generation
Domain sentiment lexicon is generated at this stage. Each term from the distant-
supervision dataset is associated with positive and negative scores. Positive (or nega-
tive) score for a term is determined as the proportion of the term’s appearance in positive
(or negative) documents given by equation 2. Separate scores for positive and negative
classes are maintain in order to suit integration with the scores obtained from the generic
lexicon (SentiWordNet). Table 1 shows example terms extracted from the dataset and
their associated positive and negative scores.
∑ tf(t)
dim
ds(t)dim = (2)
∑ tf(t)
Alldocuments
Where ds(t)dim is the sentiment score of term t for the polarity dimension dim (pos-
itive or negative) and tf(t) is document term frequency of t.
Table 1. Some terms from the domain lexicon
Sentiment Scores
Term
Positive Negative
ugh 0.077 0.923
sucks 0.132 0.868
hehe 0.896 0.104
damn 0.241 0.759
argh 0.069 0.931
thx 1 0
luv 0.958 0.042
xoxo 0.792 0.208
3.4 Aggregation Strategy for Sentiment Classification
At this stage, scores from generic and domain lexicons for each term t are combined
for sentiment prediction. The scores are combined so as to complement each other
according to the following strategy.
0,
if gs(t)dim = 0 and ds(t)dim = 0
gs(t)dim , if ds(t)dim = 0 and gs(t) > 0
Score(t)dim =
ds(t) dim , if gs(t)dim = 0 and ds(t) > 0
α × gs(t)dim + (1 − α) × ds(t)dim , if gs(t)dim > 0 and ds(t)dim > 0
The parameter, α, controls a weighted average of generic and domain scores for t
when both scores are non-zero. In this work we set α to 0.5 thereby giving equal weights
to both scores. However, we aim to investigate an optimal setting for the parameter in
the future. Finally, sentiment class for a document is determined using aggregate-and-
average method as outlined in Algorithm 1.
13
Algorithm 1 Sentiment Classification
1: INPUT: Document
2: OUTPUT: class ⊲ document sentiment class
3: Initialise: posScore, negScore
4: for all t ∈ Document do
5: if Score(t) pos > 0 then
6: posScore ← posScore + Score(t) pos
7: nPos ← nPos + 1 ⊲ increment number of positive terms
8: end if
9: if Score(t)neg > 0 then
10: negScore ← negScore + Score(t)neg
11: nNeg ← nNeg + 1 ⊲ increment number of negative terms
12: end if
13: end for
14: if posScore/nPos > negScore/nNeg then return positive
15: else return negative
16: end if
4 Evaluation
We conduct a comparative study to evaluate the proposed technique (LET). The aim of
the study is three fold, first, to investigate whether or not combining the two knowledge
sources (i.e. LET) is better than using each source alone. Second, to investigate perfor-
mance of LET compared to that of machine learning algorithms trained with distant-
supervision data since that is the state-of-the-art use of distant-supervision for sentiment
analysis. Lastly, to study the behaviour of LET on varying dataset sizes. We use hand-
labelled Twitter dataset, introduced in [9]3 for the evaluation. The dataset consists of
182 positive and 177 negative tweets.
4.1 LET Against Individual Knowledge Sources
Here, the following settings are compared:
1. LET: The proposed technique (see Algorithm 1)
2. Generic: A setting that only utilises scores obtained from the generic lexicon (Sen-
tiWorNet). In Algorithm 1, Score(t) pos (line 5) and Score(t)neg (line 9) are replaced
with gs(t) pos and gs(t)neg respectively.
3. Domain: A setting that only utilises scores obtained from the domain lexicon. In
Algorithm 1, Score(t) pos (line 5) and Score(t)neg (line 9) are replaced with ds(t)neg
and ds(t)neg respectively.
Table 2 shows result of the comparison. The LET approach performs better than
Generic and Domain. This is not suprising since LET utilises generic knowledge which
could have been omitted by Domain and also, domain knowledge which could have
3 The dataset is available from Sentiment140.com
14
Table 2. Performance accuracy of individual knowledge sources and LET
Generic Domain LET
60.33 71.26 75.27
been omitted by Generic. Also the result shows that the generated domain lexicon (Do-
main) is more effective than the general knowledge lexicon (Generic) for sentiment
analysis.
4.2 LET Against Machine Learning and Varying Dataset Sizes
Three machine learning classifiers namely Naı̈ve Bayes (NB), Support Vector Machine
(SVM) and Logistic Regression (LR) are trained with the distant-supervision dataset
and then evaluated with the human-labelled test dataset. These classifiers are selected
because they are the most commonly used for sentiment classification and typically
perform better than other classifiers. We use presence and absence (i.e. binary) feature
representation for documents and Weka [10] implementation for the classifiers. Fur-
thermore, we use subsets of the distant-supervision dataset (16000, 12000, 8000 and
4000; also balanced for positive and negative classes) in order to test the effect of vary-
ing distant-supervision dataset sizes for LET (in domain lexicon generation, see Section
3.3) and the machine learning classifiers.
Table 3. LET compared to machine learning methods on varying data sizes
XX
XXX Classifier
NB SVM LR LET
Dataset size XXXX
4,000 60.17 61.00 66.02 68.70
8,000 54.04 59.61 69.64 73.10
12,000 54.04 62.12 71.03 73.80
16,000 54.04 62.95 71.87 75.27
20,000 54.60 62.40 73.26 75.27
Table 3 shows result of the experiment. LET performs better than any of the machine
learning classifiers. This can be attributed to the fact that LET utilises generic knowl-
edge which the machine learning classifiers could not have acquired from the training
dataset, especially, as the distant-supervision dataset may contain incorrect labels. As
for the behaviour of LET and the classifiers on varying dataset sizes, they all tend to
improve in performance with increased dataset size as depicted by Fig. 3, with the ex-
ception of SVM for which the performance drops. Interestingly however, the difference
between the algorithms appeared to be maintained over the different dataset sizes. This
shows that the domain lexicon generated in LET becomes more accurate with increased
dataset size in a similar manner that a machine learning classifier becomes more accu-
rate with increased training data.
15
80
70
Classificationaccuracy
60
50
SVM
40
NB
30
LR
20
LET
10
0
4000 8000 12000 16000 20000
Datasize
Fig. 3. LET compared to machine learning methods on varying data sizes
5 Conclusions and Future Work
In this paper, we presented a novel technique for enhancing generic sentiment lexi-
con with domain knowledge for sentiment classification. The major contributions of
the paper are that we introduced a new approach of generating domain-focused lexicon
which is devoid of human involvement. Also, we introduced a novel strategy to com-
bine generic and domain lexicons for sentiment classification. Experimental evaluation
shows that the technique is effective and better than state-of-the-art machine learning
sentiment classification trained the same dataset from which our technique extracts do-
main knowledge (i.e. distant-supervision data).
As part of future work, we plan to conduct an extensive evaluation of the technique
on other social media platforms (e.g. discussion forums) and also, to extend the tech-
nique for subjective/objective classification. Similarly, we intend perform experiment
to find an optimal setting for α and improve the aggregation strategy presented.
References
[1] Arnold, I., Vrugt, E.: Fundamental uncertainty and stock market volatility. Applied Finan-
cial Economics 18(17), 1425–1440 (2008)
[2] Baccianella, S., Esuli, A., Sebastiani, F.: Sentiwordnet 3.0: An enhanced lexical resource
for sentiment analysis and opinion mining. In: Proceedings of the Annual Conference on
Language Resouces and Evaluation (2010)
[3] Baron, D.: Competing for the public through the news media. Journal of Economics and
Management Strategy 14(2), 339–376 (2005)
[4] Brin, S., Page, L.: The anatomy of a large-scale hypertextual web search engine. In: Seventh
International World-Wide Web Conference (WWW 1998) (1998)
[5] Dang, Y., Zhang, Y., Chen, H.: A lexicon-enhanced method for sentiment classification: An
experiment on online product reviews. IEEE Intelligent Systems 25, 46–53 (2010)
16
[6] Denecke, K.: Using sentiwordnet for multilingual sentiment analysis. In: ICDE Workshop
(2008)
[7] Esuli, A., Baccianella, S., Sebastiani, F.: Sentiwordnet 3.0: An enhanced lexical resource
for sentiment analysis and opinion mining. In: Proceedings of the Seventh conference on
International Language Resources and Evaluation (LREC10) (2010)
[8] Fellbaum, C.: WordNet: An Electronic Lexical Database. MIT Press (1998)
[9] Go, A., Bhayani, R., Huang, L.: Twitter sentiment classification using distant supervision.
Processing pp. 1–6 (2009)
[10] Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data
mining software: an update. SIGKDD Explor. Newsl. 11(1), 10–18 (Nov 2009)
[11] Hatzivassiloglou, V., McKeown, K.R.: Predicting the semantic orientation of adjectives.
In: Proceedings of the 35th Annual Meeting of the ACL and the 8th Conference of the
European Chapter of the ACL. pp. 174–181. New Brunswick, NJ (1997)
[12] Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of the tenth
ACM SIGKDD international conference on Knowledge discovery and data mining. pp.
168–177 (2004)
[13] Karlgren, J., Sahlgren, M., Olsson, F., Espinoza, F., Hamfors, O.: Usefulness of sentiment
analysis. In: 34th European Conference on Information Retrieval (2012)
[14] Liu, B.: Sentiment Analysis and Subjectivity, chap. Handbook of Natural Language Pro-
cessing, pp. 627–666. Chapman and Francis, second edn. (2010)
[15] Ludvigson, S.: Consumer confidence and consumer spending. The Journal of Economic
Perspectives 18(2), 29–50 (2004)
[16] Mukras, R., Wiratunga, N., Lothian, R.: Selecting bi-tags for sentiment analysis of text.
In: Proceedings of the Twenty-seventh SGAI International Conference on Innovative Tech-
niques and Applications of Artificial Intelligence (2007)
[17] Ohana, B., Tierney, B.: Sentiment classification of reviews using sentiwordnet. In: 9th
IT&T Conference, Dublin, Ireland (2009)
[18] Pang, B., Lee, L.: Polarity dataset v2.0, 2004. online (2004),
http://www.cs.cornell.edu/People/pabo/movie-review-data/.
[19] Pang, B., Lee, L.: Opinion mining and sentiment analysis. Foundations and Trends in In-
formation Retrieval 2(1), 1–135 (2008)
[20] Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? sentiment classification using machine
learning techniques. In: Proceedings of the Conference on Empirical Methods on Natural
Language Processing (2002)
[21] Pera, M., Qumsiyeh, R., Ng, Y.K.: An unsupervised sentiment classifier on summarized
or full reviews. In: Proceedings of the 11th International Conference on Web Information
Systems Engineering. pp. 142–156 (2010)
[22] Prabowo, R., Thelwall, M.: sentiment analysis: A combined approach. Journal of Informet-
rics 3(2), 143–157 (2009)
[23] Read, J.: Using emoticons to reduce dependency in machine learning techniques for sen-
timent classification. In: Proceedings of the ACL Student Research Workshop. pp. 43–48.
ACLstudent ’05, Association for Computational Linguistics, Stroudsburg, PA, USA (2005)
[24] Riloff, E., Patwardhan, S., Wiebe, J.: Feature subsumption for opinion analysis. In: Pro-
ceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
(EMNLP-06) (2006)
[25] Stone, P.J., Dexter, D.C., Marshall, S.S., Daniel, O.M.: The General Inquirer: A Computer
Approach to Content Analysis. MIT Press, Cambridge, MA (1966)
[26] Taboada, M., Brooke, J., Tofiloski, M., Voll, K., Stede, M.: Lexicon-based methods for
sentiment analysis. Computational Linguistics 37, 267–307 (2011)
17
[27] Thelwall, M., Buckley, K., Paltoglou, G.: Sentiment strength detection for the social web.
Journal of the American Society for Information Science and Technology 63(1), 163–173
(2012)
[28] Thelwall, M., Buckley, K., Paltoglou, G., Cai, D., Kappas, A.: Sentiment strength detec-
tion in short informal text. Journal of the American Society for Information Science and
Technology 61(12), 2444–2558 (2010)
[29] Turney, P., et al.: Mining the web for synonyms: Pmi-ir versus lsa on toefl. In: Proceedings
of the twelfth european conference on machine learning (ecml-2001) (2001)
[30] Turney, P.D.: Thumbs up or thumbs down? semantic orientation applied to unsupervised
classification of reviews. In: Proceedings of the Annual Meeting of the Association for
Computational Linguistics. pp. 417–424 (2002)
[31] Valitutti, R.: Wordnet-affect: an affective extension of wordnet. In: In Proceedings of the 4th
International Conference on Language Resources and Evaluation. pp. 1083–1086 (2004)
[32] Whitelaw, C., Garg, N., Argamon., S.: Using appraisal groups for sentiment analysis. In:
14th ACM International Conference on Information and Knowledge Management (CIKM
2005). pp. 625–631 (2005)
18