Rapid growth of Internet results in large amount of user-generated contents in social media, forums, blogs, and etc. Automatic analysis of this content is needed to extract valuable information from these contents. Opinion mining is a process of analyzing opinions, sentiments and emotions to recognize people’s preferences about different subjects. One of the main tasks of opinion mining is classifying a text document into positive or negative classes. Most of the researches in this field applied opinion mining for English language. Although Persian language is spoken in different countries, but there are few studies for opinion mining in Persian language. In this article, a comprehensive study of opinion mining for Persian language is conducted to examine performance of opinion mining in different conditions. First we create a Persian SENTIWORDNET using Persian WordNet. Then this lexicon is used to weight features. Results of applying three machine learning algorithms Support vector machine (SVM), naive Bayes (NB) and logistic regression are compared before and after weighting by lexicon. Experiments show support vector machine and logistic regression achieve better results in most cases and applying SO (semantic orientation) improves the accuracy of logistic regression. Increasing number of instances and using unbalanced dataset has a positive effect on the performance of opinion mining. Generally this research provides better results comparing to other researches in opinion mining of Persian language.

Awareness of others' opinions plays a crucial role in the decision making process performed by simple customers to top-level executives of manufacturing companies and various organizations. Today, with the advent of Web 2. 0 and the expansion of social networks, a vast number of texts related to people's opinions have been created. However, exploring the enormous amount of documents, various opinion sources and opposing opinions about an entity have made the process of extracting and analyzing opinions very difficult. Hence, there is a need for methods to explore and summarize the existing opinions. Accordingly, there has recently been a new trend in natural language processing science called "opinion mining". The main purpose of opinion mining is to extract and detect people’ s positive or negative sentiments (sense of satisfaction) from text reviews. The absence of a comprehensive Persian sentiment lexicon is one of the main challenges of opinion mining in Persian. In this paper, a new methodology for developing Persian Sentiment WordNet (HesNegar) is presented using various Persian and English resources. A corpus of Persian reviews developed for opinion mining studies are introduced. To develop HesNegar, a comprehensive Persian WordNet (FerdowsNet), with high recall and proper precision (based on Princeton WordNet), was first created. Then, the polarity of each synset in English SENTIWORDNET is mapped to the corresponding words in HesNegar. In the conducted tests, it was found that HesNegar has a precision score of 0. 86 a recall score of 0. 75 and it can be used as a comprehensive Persian SENTIWORDNET. The findings and developments made in this study could prove useful in the advancement of opinion mining research in Persian and other similar languages, such as Urdu and Arabic.

Rapid growth of networks and social networks results in more access to people’s opinion. These opinions contain useful information. By analyzing these opinions, people’s preferences and their positive and negative opinions about different subjects can be identified. Opinion mining is the process of analyzing people’s emotions, feelings and opinions to identify their preferences. In this article, a method for opinion mining in Persian language is introduced that is a combination of SVM and lexicon as a set of features. The lexicon is created by using SENTIWORDNET. To assess the algorithm, data of hotel domain is collected. Four cases were defined and among those cases, the case in which frequency of word multiplies with its orientation got the best result. The proposed method performs better compared to other methods in Persian opinion mining.

Analyzing user sentiments in marketing and enhancing customer experiences are essential for developing effective marketing strategies. This analysis is crucial for assessing the performance of social media platforms as communication tools. This research was practical in nature and cross-sectional in time, while utilizing both quantitative and qualitative variables within a descriptive research design. The study categorized user tweets without relying on prior knowledge or labeled data, employing fuzzy systems and an unsupervised approach. This advancement in sentiment analysis enabled researchers and practitioners to extract valuable insights from user opinions and emotions within their respective domains and platforms, thereby facilitating informed business decisions aimed at maximizing profitability. As a case study, this empirical research examined user experiences with Samsung and Apple mobile phones from 2022 to the present, classifying sentiments into positive, negative, and neutral categories. Three sentiment analysis tools—SENTIWORDNET, AFINN, and VADER—were employed to determine the polarity of the tweets. The classification results revealed a higher level of user satisfaction with Samsung mobile phones compared to Apple.IntroductionSentiment analysis plays a vital role in marketing by enabling businesses to extract emotional insights from text data, allowing for a deeper understanding of customer reactions to products and services. As social media and online platforms continue to expand rapidly, the challenge of analyzing vast amounts of textual data has intensified, highlighting the need for efficient and accurate analytical methods. This study aimed to explore and introduce an innovative approach to sentiment analysis within the context of market research and marketing strategies. By leveraging fuzzy logic—a technique adept at managing imprecise and ambiguous opinions—this research proposed a novel method for categorizing user tweets without relying on labeled data. This approach offered greater flexibility and adaptability compared to traditional methods. The primary objective was to provide managers and industry professionals with actionable insights that could inform commercial decision-making and enhance marketing strategies. Furthermore, this study addressed significant challenges associated with conventional sentiment analysis techniques, such as the time-consuming and costly nature of manual data processing and the limited availability of labeled datasets. By proposing a fuzzy logic-based system, the research aimed to overcome these limitations and offer a more efficient alternative. The central research question investigated whether a fuzzy logic approach could surpass the existing sentiment analysis methods in market studies, potentially leading to more accurate and insightful outcomes. This innovative approach has the potential to revolutionize sentiment analysis in marketing, making it more accessible and effective in understanding customer sentiments.Materials & MethodsThis study employed a comprehensive fuzzy rule-based sentiment analysis system to evaluate user opinions on Twitter. The system encompasses several detailed processes, including data collection, text preprocessing, sentiment lexicon analysis, and fuzzy classification. Data Collection: Data were collected from Twitter, focusing on tweets related to Apple and Samsung smartphones from 2022 onwards. Approximately 100 tweets for each company were selected and stored in separate CSV files. Text Preprocessing: During preprocessing, URLs and @ symbols were removed and common contractions, such as "can’t", were expanded to "cannot". Hashtags were stripped of the "#" symbol to prepare the text for analysis. These steps reduced ambiguity and enhanced sentiment interpretation. Sentiment Lexicon Analysis: Three sentiment lexicon tools—SENTIWORDNET, AFINN, and VADER—were utilized to calculate positive and negative scores for the tweets. These tools facilitated the labeling and analysis of sentiment. Fuzzy System: A fuzzy rule-based system with 9 proposed rules was developed to determine sentiment polarity. This unsupervised system classified sentiment based on a set of carefully defined rules. Comparison of Lexicon Tools: The performance of the sentiment analysis tools was evaluated using datasets from Samsung and Apple. Results indicated that AFINN demonstrated the highest accuracy, recall, and F1 scores among the tools, proving to be the most effective for analyzing social media posts. AFINN outperformed SENTIWORDNET and VADER in both precision and recall. The choice of the best lexicon tool depended on the evaluation metrics and the characteristics of the dataset.Research FindingsThis section presented a comprehensive analysis of the performance of the fuzzy rule-based sentiment analysis system, utilizing the AFINN lexicon to evaluate Twitter data related to Samsung and Apple. The sentiment analysis revealed a 60% satisfaction rate for Samsung products, while Apple products had a satisfaction rate of 50%. Negative comments accounted for 20% of tweets related to Samsung compared to 14% for Apple. Neutral comments represented 20 and 36% of Samsung- and  Apple-related tweets, respectivdely. This distribution indicated that Samsung users generally expressed more positive sentiments toward the brand compared to Apple users. However, Apple received a higher percentage of neutral comments, suggesting a more nuanced and varied perception of the brand. The lower percentage of negative comments for Apple might imply that while fewer users were dissatisfied, there was a greater level of indifference or neutrality compared to Samsung. The analysis highlighted the effectiveness of the AFINN tool in sentiment classification. Compared to other sentiment analysis tools, AFINN demonstrated superior accuracy and efficiency in processing Twitter data. The results indicated that the classification of AFINN and scoring of sentiments were both reliable and consistent, reinforcing its value as a tool for social media sentiment analysis. This effectiveness was crucial for gaining accurate insights into user opinions and brand perceptions, providing a valuable resource for marketers seeking to understand and respond to consumer sentiments more effectively.Discussion of Results & ConclusionThis study highlighted the effectiveness of an unsupervised fuzzy system in accurately identifying sentiments in tweets related to Samsung and Apple, achieving accuracies of 74.44 and 77.16%, respectively. The fuzzy system operated independently of prior training data and demonstrated high precision in sentiment classification, making it a highly efficient tool for analyzing large-scale data. This approach was particularly valuable for handling the vast and diverse nature of social media data, where traditional supervised methods might fall short. Additionally, the AFINN lexicon outperformed SENTIWORDNET and VADER in terms of precision, recall, and F1 score. This validation underscored the effectiveness of AFINN in capturing nuanced sentiment expressions, which was crucial for accurate sentiment analysis. The findings indicated that Samsung products generally achieved a higher level of customer satisfaction compared to Apple products. This insight could be instrumental for Apple management, providing a clear indication of areas that required improvement. The sentiment analysis enabled both companies to identify strengths and weaknesses in their products and allowed for a strategic focus on positive attributes in marketing campaigns. By leveraging detailed customer feedback, businesses can gain a better understanding of market trends and more accurately predict customer behavior. The fuzzy system’s cost-effectiveness and resource efficiency further enhance its value, supporting improved managerial decision-making and strategic planning. Overall, this approach provides a robust and scalable solution for sentiment analysis, offering significant advantages over traditional methods.

Big data analytics is one of the most important subjects in computer science. Today, due to the increasing expansion of Web technology, a large amount of data is available to researchers. Extracting information from these data is one of the requirements for many organizations and business centers. In recent years, the massive amount of Twitter's social networking data has become a platform for data mining research to discover facts, trends, events, and even predictions of some incidents. In this paper, a new framework for clustering and extraction of information is presented to analyze the sentiments from the big data. The proposed method is based on the keywords and the polarity determination which employs seven emotional signal groups. The dataset used is 2077610 tweets in both English and Persian. We utilize the Hive tool in the Hadoop environment to cluster the data, and the Wordnet and SENTIWORDNET 3. 0 tools to analyze the sentiments of fans of Iranian athletes. The results of the 2016 Olympic and Paralympic events in a one-month period show a high degree of precision and recall of this approach compared to other keyword-based methods for sentiment analysis. Moreover, utilizing the big data processing tools such as Hive and Pig shows that these tools have a shorter response time than the traditional data processing methods for preprocessing, classifications and sentiment analysis of collected tweets.