Impact of Negation and AnA-Words on Overall Sentiment Value of the Text Written in the Bosnian Language

Abstract

In this manuscript, we present our efforts to develop an accurate sentiment analysis model for Bosnian-language tweets which incorporated three elements: negation cues, AnA-words (referring to maximizers, boosters, approximators, relative intensifiers, diminishers, and minimizers), and sentiment-labeled words from a lexicon. We used several machine-learning techniques, including SVM, Naive Bayes, RF, and CNN, with different input parameters, such as batch size, number of convolution layers, and type of convolution layers. In addition to these techniques, BOSentiment is used to provide an initial sentiment value for each tweet, which is then used as input for CNN. Our best-performing model, which combined BOSentiment and CNN with 256 filters and a size of 4×4, with a batch size of 10, achieved an accuracy of over 92%. Our results demonstrate the effectiveness of our approach in accurately classifying the sentiment of Bosnian tweets using machine-learning techniques, lexicons, and pre-trained models. This study makes a significant contribution to the field of sentiment analysis for under-researched languages such as Bosnian, and our approach could be extended to other languages and social media platforms to gain insight into public opinion.

Annotated Lexicon for Sentiment Analysis in the Bosnian Language

“…The Bosnian sentiment-annotated lexicon is presented and analysed in this paper. For this purpose, our data consists of the "core" lexicon (Jahić and Vičič, 2023b), a list of stopwords, and a list of AnAwords (Affirmative and Non-affirmative words, such as "ekstremno" ("vrlo") -extremely, "jedva" -barely) (Jahić and Vičič, 2023a), as clarified in Figure 1. The lexicon creation process is comprised of taking entries (word forms) from the Slovene sentiment lexicon KSS 1.1 (Kadunc, 2016) and translating them into Bosnian.…”

“…In addition to lexicons, two other groups of words -stopwords (394 of them) and AnAwords (Affirmative and Non-affirmative words) -play a significant role in this process. Jahić and Vičič (2023a) pointed out that stopwords usually refer to the most common words in a language and that there is no single universal list of these.…”

Dataset of sentiment tagged language resources for Bosnian language

“… Data source location Primary data source (partial): Slovenian sense annotated lexicon presented in Kadunc [17] . Data source location: University of Primorska, UPFAMNIT, Glagoljaska 8, 6000 Koper, Slovenia Data accessibility Sentiment polarity lexicon of Bosnian language Repository: Zenodo DOI: 10.5281/zenodo.10373141 URL: https://doi.org/10.5281/zenodo.10373141 AnAwords list, Stopwords list, and Polarity Shifters list Repository: Zenodo DOI: 10.5281/zenodo.10373107 URL: https://doi.org/10.5281/zenodo.10373107 Related research article Jahić and Vičič [1] present an impact of negation and attenuators on the overall quality of sentiment tagging process for Bosnian language. …”