RESEARCH & MEASUREMENTS

HOW I MEASURE THE SCRAPED REVIEWS

POLARITY - Sentiment analysis is the process of using natural language processing (NLP) and machine learning techniques to identify, extract, and quantify subjective information from textual data. Polarity in sentiment analysis refers to the direction and degree of sentiment expressed in a given piece of text, and is often measured on a scale from negative to positive. Web scraping is the process of automatically extracting data from websites using web crawlers or bots. When conducting sentiment analysis through web scraping, polarity can be determined by analyzing the sentiment of the text scraped from the website. This can be done using various NLP techniques such as text classification, sentiment lexicons, and machine learning algorithms. The resulting polarity score can then be used to gain insights into the overall sentiment of the website or specific pages, products, or topics.



MY MEASUREMENTS: If the polarity score is between -1.0 and -0.15, the sentiment label assigned is "Bad". If it is between -0.14 and 0.05, the label assigned is "Neutral". If the polarity score is between 0.06 and 0.45, the label assigned is "Okay". And if the polarity score is outside of these ranges, the label assigned is "Good".

SUBJECTIVITY - Subjectivity is another important aspect of sentiment analysis, in addition to polarity. While polarity measures the direction and degree of sentiment expressed in a piece of text, subjectivity measures how subjective or objective the language used in the text is. In sentiment analysis, subjectivity is often measured on a scale from 0 to 1, where 0 indicates complete objectivity (i.e., factual statements with no emotional content), and 1 indicates complete subjectivity (i.e., emotional or opinionated statements with no factual basis). For example, a review that includes phrases such as "I loved it" or "it was terrible" would be considered subjective, as it expresses a personal opinion or emotion. On the other hand, a review that simply states factual information about a product or service without expressing any personal opinion would be considered objective. Subjectivity scores can be useful for identifying the level of personal bias or opinion in a piece of text, and can be used in conjunction with polarity scores to gain a more nuanced understanding of the sentiment expressed in the text. For example, a review with a high positive polarity score and a high subjectivity score may indicate strong positive emotions and personal attachment to the product or service being reviewed, while a review with a low polarity score and a low subjectivity score may indicate a lack of strong emotions or opinions.



MY MEASUREMENTS: If the subjectivity score is less than or equal to 0.45, the label assigned is 'Factual'. This means that the language used in the review is relatively objective and factual, with minimal personal opinion or emotional content. If the subjectivity score is greater than 0.45, the label assigned is 'Personal Opinion'. This means that the language used in the review is relatively subjective and includes a significant amount of personal opinion or emotional content.

SENTIMENTS - In sentiment analysis, the goal is to automatically identify and quantify the sentiment expressed in a piece of text, typically by assigning a numerical score to the text based on its polarity (i.e., the degree to which it expresses positive or negative sentiment). For example, a positive sentiment might be expressed through language such as "amazing", "fantastic", or "delightful", while a negative sentiment might be expressed through language such as "terrible", "disappointing", or "awful". Sentiment analysis can be applied to a wide range of textual data, including customer reviews, social media posts, news articles, and more. By analyzing the sentiments expressed in this data, businesses and organizations can gain insights into the attitudes and opinions of their customers or stakeholders, and use this information to inform their decision-making processes.

SCRAPELY OFFERS not only businesses but customers insights on places they want to visit with family and friends as well.



SUBJECTIVES - In sentiment analysis, subjectivity is often used to gain a deeper understanding of the opinions and attitudes expressed in a piece of text. For example, a highly subjective review of a product might contain language such as "I absolutely loved the services and the room was great", while a more objective review might contain language such as "This hotel was extremely clean and had unbelieveable food". By measuring the subjectivity of a piece of text, analysts can gain insights into the degree to which personal opinions and emotions are driving the sentiment expressed in the text. Subjectivity analysis can be useful in a wide range of applications, including marketing research, product development, and customer service. By identifying the degree of subjectivity in customer feedback, organizations can gain a more nuanced understanding of their customers' attitudes and opinions, and use this information to inform business decisions and improve customer satisfaction.