Sentiment lexicons for sentiment analysis offer a simple, yet effective way to obtain the prior sentiment information of opinionated words in texts. However, words' sentiment orientations and strengths often change throughout various contexts in which the words appear. In this paper, we propose a lexicon adaptation approach that uses the contextual semantics of words to capture their contexts in tweet messages and update their prior sentiment orientations and/or strengths accordingly. We evaluate our approach on one state-of-the-art sentiment lexicon using three different Twitter datasets. Results show that the sentiment lexicons adapted by our approach outperform the original lexicon in accuracy and F-measure in two datasets, but give similar accuracy and slightly lower F-measure in one dataset.
Sentiment analysis on Twitter has been attracting much attention recently due to the
rapid growth in Twitter’s popularity as a platform for people to express their opinions
and attitudes towards a great variety of topics. Most existing approaches to Twitter
sentiment analysis can be categorised into machine learning [
Lexicon-based approaches use lexicons of words weighted with their sentiment
orientations to determine the overall sentiment in texts. These approaches have shown
to be more applicable to Twitter data than machine learning approaches, since they do
not require training from labelled data and therefore, they offer a domain-independent
sentiment detection [
To overcome the above limitations, several lexicon bootstrapping and adaptation
methods have been previously proposed. However, these methods are either supervised
[
In this paper we propose an unsupervised approach for adapting sentiment lexicons based on the contextual semantics of their words in a tweet corpus. In particular, our approach studies the co-occurrences between words to capture their contexts in tweets and update their prior sentiment orientations and/or sentiment strengths in a given lexicon accordingly.
As a case study we apply our approach on Thelwall-Lexicon [
In the rest of this paper, related work is discussed in Section 2, and our approach is presented in Sections 3. Experiments and results are presented in Sections 4. Discussion and future work are covered in Section 5. Finally, we conclude our work in Section 6. 2
Exiting approaches to bootstrapping and adapting sentiment lexicons can be categorised
into dictionary and corpus-based approaches. The dictionary-based approach [
Alternatively, the corpus-based approach measures the sentiment orientation of
words automatically based on their association to other strongly opinionated words in a
given corpus [
Following the aforementioned approaches, several lexicons such as MPQA [
Quite few sentiment lexicons have been recently built to work specifically with social
media data, such as Thelwall-Lexicon [
Aiming at addressing the above limitations we have designed our lexicon-adaptation approach in away that allows to (i) work in unsupervised fashion, avoiding the need for labelled data, and (ii) exploit the contextual semantics of words. This allows capturing their contextual information in tweets and update their prior sentiment orientation and strength in a given sentiment lexicon accordingly. 3
The main principle behind our approach is that the
sentiment of a term is not static, as found in general-purpose Tweets Extract
wsehnitcimhethnet lteexrmicoinssu,sbeudt, ria.eth.,eirt ddeeppeennddss oonn tihtse ccoonntteexxttuianl SeLenxtiimcoennt CSoenntteimxteunatl
semantics.3 Therefore, our approach functions in two main
steps as shown in Figure 1. First, given a tweet collection Rule-based Lexicon Adaptation
and a sentiment lexicon, the approach builds a contextual
semantic representation for each unique term in the tweet Adapted Lexicon
collection and subsequently uses it to derive the term’s
contextual sentiment orientation and strength. The SentiCircle Fig. 1. The systematic
workrepresentation model is used to this end [
The first step in our pipeline is to capture the words contextual semantics and sentiment
in tweets. To this end, we use our previously proposed semantic representation model,
SentiCircle [
Following the distributional hypothesis that words that co-occur in similar contexts
tend to have similar meaning [
N Nci 3 We define context as a textual corpus or a set of tweets. where f (ci, m) is the number of times ci occurs with m in tweets, N is the total number of terms, and Nci is the total number of terms that occur with ci. Note that all terms’ radii in the SentiCircle are normalised. Also, all angles’ values are in radian. tToheentcroigdoentohmeectornictepxrtoupaelrsteiemsaonftitchseoSfeantteiCrmircalse saelnlotiwmseunst Very Positive Y +1 Positive toirmieennttaotifotnheantedrmse,nit.iem.,eanpt osstriteinvgetyh.vYal-uaexidsedneofitenseas pthoesistievne- yi ri Ci ssetrnetni mgtehnotfanthdevtiecremv.eTrshae. TsmhealXle-ratxhise dxevfianleuset,htehesesntrtoimngeenrt -1 m θi xi +1 X the sentiment.4 This, in turn, divides the circle into four sentiment quadrants. Terms in the two upper quadrants have a positive sentiment (sin ✓ > 0), with upper left quadrant Very Negative -1 Negative representing stronger positive sentiment since it has larger rθii==TPDriOorC_(SCei)ntiment (Ci) angle values than those in the top right quadrant. Simi- Fig. 2. SentiCircle of a term larly, terms in the two lower quadrants have negative sen- m. Neutral region is shaded timent values (sin ✓ < 0). Moreover, a small region called in blue. the “Neutral Region” can be defined. This region, as shown in Figure 2, is located very close to X-axis in the “Positive” and the “Negative” quadrants only, where terms lie in this region have very weak sentiment (i.e, |✓ | t 0). Calculating Contextual Sentiment In summary, the Senti-Circle of a term m is composed by the set of (x, y) Cartesian coordinates of all the context terms of m. An effective way to compute the overall sentiment of m is by calculating the geometric median of all tChierlpcoein⌦ts, itnheit2sDSegnetioCmirectlrei.cFmoremdiaalnlyg,fiosrdaegfiinveedn saest: ogf=n paorignmts i(npg12 , Rp22, P...n,pn) in a Sentii=1 k|pi g||2.
We call the geometric median g the SentiMedian as its position in the SentiCircle determines the final contextual-sentiment orientation and strength of m.
Note that the boundaries of the neutral region can be computed by measuring the
density distribution of terms in the SentiCircle along the Y-axis. In this paper we use
similar boundaries to the ones used in [
The second step in our approach is to update the sentiment lexicon with the terms’
contextual sentiment information extracted in the previous step. As mentioned earlier, in
this work we use Thelwall-Lexicon [
Thelwall-Lexicon consists of 2546 terms coupled with integer values between -5 (very
negative) and +5 (very positive). Based on the terms’ prior sentiment orientations and
strengths (SOS), we group them into three subsets of 1919 negative terms (SOS2 [-2,-5]),
398 positive terms (SOS2 [
The adaptation method uses a set of antecedent-consequent rules that decides how the prior sentiment of the terms in Thelwall-Lexicon should be updated according to the positions of their SentiMedians (i.e., their contextual sentiment). In particular, for a term m, the method checks (i) its prior SOS value in Thelwall-Lexicon and (ii) the SentiCircle 4 This is because cos ✓ < 0 for large angles. quadrant in which the SentiMedian of m resides. The method subsequently chooses the best-matching rule to update the term’s prior sentiment and/or strength.
Table 1 shows the complete list of rules in the proposed method. As noted, these rules are divided into updating rules, i.e., rules for updating the existing terms in ThelwallLexicon, and expanding rules, i.e., rules for expanding the lexicon with new terms. The updating rules are further divided into rules that deal with terms that have similar prior and contextual sentiment orientations (i.e., both positive or negative), and rules that deal with terms that have different prior and contextual sentiment orientations (i.e., negative prior, positive contextual sentiment and vice versa).
Although they look complicated, the notion behind the proposed rules is rather simple: Check how strong the contextual sentiment is and how weak the prior sentiment is ! update the sentiment orientation and strength accordingly. The strength of the contextual sentiment can be determined based on the sentiment quadrant of the SentiMedian of m, i.e., the contextual sentiment is strong if the SentiMedian resides in the “Very Positive” or “Very Negative” quadrants (See Figure 2). On the other hand, the prior sentiment of m (i.e., priorm) in Thelwall-Lexicon is weak if |priorm| 6 3 and strong otherwise.
Updating Rules (Similar Sentiment Orientations) Id Antecedents Consequent 1 (|prior| 6 3) ^ (SentiMedian 2 / StrongQuadrant) |prior| = |prior| + 1 2 (|prior| 6 3) ^ (SentiMedian 2 StrongQuadrant) |prior| = |prior| + 2 3 (|prior| > 3) ^ (SentiMedian 2 / StrongQuadrant) |prior| = |prior| + 1 4 (|prior| > 3) ^ (SentiMedian 2 StrongQuadrant) |prior| = |prior| + 1
Updating Rules (Different Sentiment Orientations) 5 (|prior| 6 3) ^ (SentiMedian 2 / StrongQuadrant) |prior| = 1 6 (|prior| 6 3) ^ (SentiMedian 2 StrongQuadrant) prior = prior 7 (|prior| > 3) ^ (SentiMedian 2 / StrongQuadrant) |prior| = |prior| 1 8 (|prior| > 3) ^ (SentiMedian 2 StrongQuadrant) prior = prior 9 (|prior| > 3) ^ (SentiMedian 2 N eutralRegion) |prior| = |prior| 1 10 (|prior| 6 3) ^ (SentiMedian 2 N eutralRegion) |prior| = 1
Expanding Rules 11 SentiMedian 2 N eutralRegion (|contextual| = 1) ^ AddT erm 12 SentiMedian 2 / StrongQuadrant (|contextual| = 3) ^ AddT erm 13 SentiMedian 2 StrongQuadrant (|contextual| = 5) ^ AddT erm Table 1. Adaptation rules for Thelwall-Lexicon, where prior: prior sentiment value, StrongQuadrant: very negative/positive quadrant in the SentiCircle, Add: add the term to Thelwall-Lexicon.
For example, the word “revolution” in Thelwall-Lexicon has a weak negative sentiment (prior=-2) while it has a neutral contextual sentiment since its SentiMedian resides in the neutral region (SentiM edian 2 N eutralRegion). Therefore, rule number 10 is applied and the term’s prior sentiment in Thelwall lexicon will be updated to neutral (|prior| = 1). In another example, the words “Obama” and “Independence” are not covered by the Thelwall-Lexicon, and therefore, they have no prior sentiment. However, their SentiMedians reside in the “Positive” quadrant in their SentiCircles, and therefore rule number 12 is applied and both terms will be assigned with a positive sentiment strength of 3 and added to the lexicon consequently. 4
We evaluate our approach on Thelwall-Lexicon using three adaptation settings: (i) the
update setting where we update the prior sentiment of existing terms in the lexicon, (ii)
The expand setting where we expand Thelwall-Lexicon with new opinionated terms, and
(iii) the update+expand setting where we try both aforementioned settings together. To
this end, we use three Twitter datasets OMD, HCR and STS-Gold. Numbers of positive
and negative tweets within these datasets are summarised in Table 2, and detailed in the
references added in the table. To evaluate the adapted lexicons under the above settings,
we perform binary polarity classification on the three datasets. To this end, we use the
sentiment detection method proposed with Thelwall-Lexicon [
Applying our adaptation approach to Thelwall-Lexicon results in dramatic changes in it. Table 3 shows the percentage of words in the three datasets that were found in Thelwall-Lexicon with their sentiment changed after adaptation. One can notice that on average 9.61% of the words in our datasets were found in the lexicon. However, updating the lexicon with the contextual sentiment of words resulted in 33.82% of these words flipping their sentiment orientation and 62.94% changing their sentiment strength while keeping their prior sentiment orientation. Only 3.24% of the words in Thelwall-Lexicon remained untouched. Moreover, 21.37% of words previously unseen in the lexicon were assigned with contextual sentiment by our approach and added to Thelwall-Lexicon subsequently.
Table 4 shows the average results of binary sentiment classification performed on our datasets using (i) the original Thelwall-Lexicon (Original), (ii) Thelwall-Lexicon induced under the update setting (Updated), and (iii) Thelwall-Lexicon induced under the update+expand setting.5 The table reports the results in accuracy and three sets of precision (P), recall (R), and F-measure (F1), one for positive sentiment detection, one for negative, and one for the average of the two.
From these results in Table 4, we notice that the best classification performance in accuracy and F1 is obtained on the STS-Gold dataset regardless the lexicon being used. We also observe that the negative sentiment detection performance is always higher than the positive detection performance for all datasets and lexicons.
As for different lexicons, we notice that on OMD and STS-Gold the adapted lexicons outperform the original lexicon in both accuracy and F-measure. For example, on OMD the adapted lexicon shows an average improvement of 2.46% and 4.51% in accuracy and F1 respectively over the original lexicon. On STS-Gold the performance improvement is 5 Note that in this work we do not report the results obtained under the expand setting since no improvement was observed comparing to the other two settings. We demonstrated the value of using contextual semantics of words for adapting sentiment lexicons from tweets. Specifically, we used Thelwall-Lexicon as a case study and evaluated its adaptation to three datasets of different sizes. Although the potential is palpable, our results were not conclusive, where a performance drop was observed in the HCR dataset using our adapted lexicons. Our initial observations suggest that the quality of our approach might be dependent on the sentiment class distribution in the dataset. Therefore, a deeper investigation in this direction is required.
We used the SentiCircle approach to extract the contextual semantics of words from tweets. In future work we will try other contextual semantic approaches and study how the semantic extraction quality affects the adaptation performance.
Our adaptation rules in this paper are specific to Thelwall-Lexicon. These rules, however, can be generalized to other lexicons, which constitutes another future direction of this work.
All words which have contextual sentiment were used for adaptation. Nevertheless, the results conveyed that the prior sentiments in the lexicon might need to be unchanged for words of specific syntactical or linguistic properties in tweets. Part of our future work is to detect and filter those words that are more likely to have stable sentiment regardless the contexts in which they appear. 6
In this paper we proposed an unsupervised approach for sentiment lexicon adaptation from Twitter data. Our approach extracts the contextual semantics of words and uses them to update the words’ prior sentiment orientations and/or strength in a given sentiment lexicon. The evaluation was done on Thelwall-Lexicon using three Twitter datasets. Results showed that lexicons adapted by our approach improved the sentiment classification performance in both accuracy and F1 in two out of three datasets.
This work was supported by the EU-FP7 project SENSE4US (grant no. 611242).