A Negation Handling Technique for Sentiment Analysis

Diamantini, Claudia; Mircoli, Alex; Potena, Domenico

doi:10.1109/cts.2016.0048

Cited by 29 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The more relieved a user is, the less likely they are to spread negativity. Several researches showed that visualizing images of natural views and landscapes, whether they are viewed as 2D photographs, or scenes, resulted in healthy rewinding effects, such as canceling visual and attentional areas of the brain, removing eye blinking and stress [13,22]. The study [22] investigated 37 articles showing real evidence of the physiological results of witnessing natural views, through on indoor setting experiments-Exposures to display stimuli, confirmed that viewing natural scenery created a physiological relaxing state.…”

Section: Nature's Effectmentioning

confidence: 81%

Polarity Switch within Social Networks

Abas¹,

Addou²,

Rachik³

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

It is the age of information. Social networks are the main reason why, following the increasing activity of online users. With this comes a big impact on the real world, it can be positive and highly negative as well. Therefore, research in this field is highly needed for the betterment of societal behaviors within social networks, to minimize the negative impact. When a negatively polarized message spreads over time, it is eventually exposed to most users of that social network where it is spreading. Social network communities start behaving in a negatively polarized way, due to the negative nature of the propagation of information. In order to optimize technological intervention to the benefit of humanity, in this paper an approach is elaborated in order to help switch the dominant polarity in the case of negativity. The platform of reference is Twitter, since it classifies trends per area, which polarities' dominate within the social network. To achieve that, an extraction as well as a sentiment analysis method are developed to initiate the positive polarity introduction in the network. The idea behind introducing a positive polarity in a network, relies on the studies of the positive effect nature has on users. The positively polarized promoted content is selected from sponsored content of users who consent to spreading their posts.

show abstract

Section: Nature's Effectmentioning

confidence: 81%

Polarity Switch within Social Networks

Abas¹,

Addou²,

Rachik³

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…The first and most common approaches employed by sentiment analysis are based on features like unigrams, in terms of their presence or frequency, Part Of Speech (POS) tags and term position [19], opinion words and sentences [20], negations [21] and syntactic dependencies [22]. Some approaches have shown effective performance in text categorization, such as Support Vector Machine (SVM) [23], Multinomial Naïve Bayes (MNB) [24] and Maximum Entropy (ME) classifiers and derived ensembles [22,25], even if their classification skills remain limited by the high training costs due to the need for a broader vocabulary, i.e., more words from which more features can be extracted [26] to be used in conjunction with machine learning algorithms for sentiment classification.…”

Section: Techniques For Sentiment Analysismentioning

confidence: 99%

An Effective BERT-Based Pipeline for Twitter Sentiment Analysis: A Case Study in Italian

Pota

Ventura

Catelli

et al. 2020

Sensors

View full text Add to dashboard Cite

Over the last decade industrial and academic communities have increased their focus on sentiment analysis techniques, especially applied to tweets. State-of-the-art results have been recently achieved using language models trained from scratch on corpora made up exclusively of tweets, in order to better handle the Twitter jargon. This work aims to introduce a different approach for Twitter sentiment analysis based on two steps. Firstly, the tweet jargon, including emojis and emoticons, is transformed into plain text, exploiting procedures that are language-independent or easily applicable to different languages. Secondly, the resulting tweets are classified using the language model BERT, but pre-trained on plain text, instead of tweets, for two reasons: (1) pre-trained models on plain text are easily available in many languages, avoiding resource- and time-consuming model training directly on tweets from scratch; (2) available plain text corpora are larger than tweet-only ones, therefore allowing better performance. A case study describing the application of the approach to Italian is presented, with a comparison with other Italian existing solutions. The results obtained show the effectiveness of the approach and indicate that, thanks to its general basis from a methodological perspective, it can also be promising for other languages.

show abstract

“…The proposed traditional approaches have been proved to get good results by proper feature engineering. Thus, the commonly used features by these approaches in sentiment analysis are: part of speech (POS) tags [8], term position [8], opinion words and sentences [6,[31][32][33], negation [33], term presence and frequency [34], and syntactic dependency [35]. In quest of details about these features, you can refer to [2,8].…”

Section: Traditional Approaches For Sentiment Analysismentioning

confidence: 99%

“…Later, different lexicons were proposed such as WordNet, WordNet-Affect, SenticNet, MPQA, and SentiWordNet [31]. Following the popularity of lexicons, extensive research has been done for sentiment analysis based on lexicons [6,31,33,38]. These approaches do not require the training dataset.…”

Section: Traditional Approaches For Sentiment Analysismentioning

confidence: 99%