Loading...
Search for:
sentiment-analysis
0.004 seconds
Total 30 records
Constructing Brand Perceptual Maps from Consumer Reviews of Online Shops Using Machine Learning
, M.Sc. Thesis Sharif University of Technology ; Najmi, Manoochehr (Supervisor)
Abstract
Brand perceptual map is a practical tool for visualizing the position of a brand and its competitors in the mind of customers. In traditional ways of building a brand perceptual map, the researcher identifies important aspects of the product and designs a questionnaire to measure the scores of different brands to gather the required information from users. With the increasing development of online shopping, users have been voluntarily registering their reviews in online shops, in a free and unstructured manner, and have created valuable data sources in these online stores. Due to the large size of registered reviews, processing them requires the use of automated methods in computers. In...
Stock Market Prediction Using Textual Data from News and Social Networks
, M.Sc. Thesis Sharif University of Technology ; Akhavan Niaki, Taghi (Supervisor)
Abstract
One of the influential factors affecting the future price trends of a stock is the public sentiment surrounding that particular stock. In recent years, researchers have employed Natural Language Processing (NLP) techniques to analyze textual data present on social networks, aiming to investigate public opinions. However, there has been limited attention given to validating the users expressing opinions concerning the stock market. Much of the opinions shared on social networks lack a thorough examination and analysis of the market, often being solely based on the author's sentiments. This research endeavors to validate active users on the social network 'X' (Twitter) by developing a...
Persian sentiment lexicon expansion using unsupervised learning methods
, Article 9th International Conference on Computer and Knowledge Engineering, ICCKE 2019, 24 October 2019 through 25 October 2019 ; 2019 , Pages 461-465 ; 9781728150758 (ISBN) ; Hashemi Devin, K ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2019
Abstract
Sentiment analysis, is a subfield of natural language processing that aims at opinion mining to analyze thoughts, orientation and, evaluation of users within some texts. The solution to this problem includes two main steps: extracting aspects and determining users' positive or negative sentiments with respect to the aspects. Two main challenges of sentiment analysis in the Persian language are lack of comprehensive tagged data sets and use of colloquial language in texts. In this paper we propose, a system to specify and extract sentiment words using unsupervised methods in the Persian language that also support colloquial words. Additionally, we also proposed and implemented a state-of-art...
Persian sentiment analysis of an online store independent of pre-processing using convolutional neural network with fastText embeddings
, Article PeerJ Computer Science ; Volume 7 , 2021 , Pages 1-22 ; 23765992 (ISSN) ; Yazdinejad, M ; Guo, Y ; Sharif University of Technology
PeerJ Inc
2021
Abstract
Sentiment analysis plays a key role in companies, especially stores, and increasing the accuracy in determining customers’ opinions about products assists to maintain their competitive conditions. We intend to analyze the users’ opinions on the website of the most immense online store in Iran; Digikala. However, the Persian language is unstructured which makes the pre-processing stage very difficult and it is the main problem of sentiment analysis in Persian. What exacerbates this problem is the lack of available libraries for Persian pre-processing, while most libraries focus on English. To tackle this, approximately 3 million reviews were gathered in Persian from the Digikala website using...
Analyzing Customers' Reviews in Online Businesses and their Impact on Product Sales
, M.Sc. Thesis Sharif University of Technology ; Majid, Rafiee (Supervisor)
Abstract
In recent years, the attention of marketing researchers has shifted from numerical product rating to user-generated content. Because of this, customers' online reviews now play a very important role in the destiny of Internet businesses. Today, huge and comprehensive platforms have been developed to record and analyze online customer reviews. This type of unstructured data that users and Internet shoppers create based on their experiences of using products and services, has a significant impact on gaining and losing the trust of other users. After reading each review, each user can express their opinion about the usefulness of that comment, which can be seen by others. Large Internet...
Pre-trained Model utilization Using Cross-lingual Methods
, M.Sc. Thesis Sharif University of Technology ; Sameti, Hossein (Supervisor) ; Motahari, Abolfazl (Supervisor)
Abstract
Following dramatic changes after using deep learning method as a solution for Natural Language Processing tasks, Transformer architecture get popular. Based on that, then BERT Language model presented and get state-of-the-art as a solution for a lot of language processing tasks. It was a turning point in Natural Language Processing field. Also, in cross-lingual methods research line motivated by developing a common space for representation of language units, e.g. words, sentences, in more that one language, get some remarkable improvements. However, for languages distant from English such as Persian or Arabic the methods' performance was not clear. In this work, we performed some innovative...
Improving Pre-trained Language Model for Sentiment Analysis
, M.Sc. Thesis Sharif University of Technology ; Sameti, Hossein (Supervisor)
Abstract
Sentiment analysis is a useful problem which could serve a variety of fields from business intelligence to social studies and even health studies.Besides, solutions using Pre-Trained models have showed superiority over other ones. Hence we attempted to solve sentiment analysis by the help of pre-trained models. Using SemEval 2022 Task 10 formulation of sentiment analysis and proposing a new method, we improved the task baselines. Task baselines have used Dependency Graph Parsing and LSTM in their solutions respectively.Our solution outperformed the best one across all datasets and according to the Sentiment Graph F1 metric, defined in the task description, by at least 2 points. In our...
The Predicting Power of Investors’ Sentiment for Cryptocurrency Returns
, M.Sc. Thesis Sharif University of Technology ; Arian, Hamid Reza (Supervisor) ; Hagh Panah, Farshad (Co-Supervisor)
Abstract
Classical financial literature believes that people's decisions in financial markets are rational and that asset prices remain at their intrinsic value. On the other hand, behavioral finance literature believes that there are limitations in investors' decision-making and the impact of decisions on emotions, and states that investors' emotions directly affect asset prices. The aim of this research is to investigate which of the famous indicators introduced in the literature as a representative of the emotional behavior of investors has a better performance in predicting the returns of cryptocurrencies. For this purpose, in the first step, the information related to the calculation of three...
Identifying, Score Predicting, and Investigating the Factors Affecting Green Restaurants' Customers' Satisfaction
, M.Sc. Thesis Sharif University of Technology ; Khalili Nasr, Arash (Supervisor)
Abstract
Like other industries and research literature, tourism and hospitality have increasingly interpreted and analyzed the vast amount of user-generated content and online reviews to address practical and theoretical issues concerning customer experience and satisfaction. One of the most underdeveloped data-driven research streams in tourism and hospitality is green restaurant research. To address the gap regarding the actual behaviors, perceptions, and anticipations of such restaurants' customers, this study first used a new advanced topic modeling algorithm to identify hidden topics of customer reviews. The result suggests that customers mostly perceive food-related green attributes when it...
Sentiment analysis on stock social media for stock price movement prediction
, Article Engineering Applications of Artificial Intelligence ; Volume 85 , 2019 , Pages 569-578 ; 09521976 (ISSN) ; Beigy, H ; Sharif University of Technology
Elsevier Ltd
2019
Abstract
The opinions of other people are an essential piece of information for making informed decisions. With the increase in using the Internet, today the web becomes an excellent source of user's viewpoints in different domains. However, in one hand, the growing volume of opinionated text and on the other hand, complexity caused by contrast in user opinion, makes it almost impossible to read all of these reviews and make an informed decision. These requirements have encouraged a new line of research on mining user reviews, which is called opinion mining. User's viewpoints could change during the time, and this is an important issue for companies. One of the most challenging problems of opinion...