Prediction of User’s Interest Based on Urdu Tweets

Mustafa, Faizan ul; Ashraf, Imran; Baqir, Anees; Ahmad, Usman; Malik, Sayyam; Mehmood, Sadaf

doi:10.1109/raeecs50817.2020.9265694

Cited by 5 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Valuable insights into customer feedback can be provided by topic modeling, according to the results, enabling businesses to improve their products and services based on customer preferences. The research described in 2020 [21] utilized machine learning algorithms to predict user interests based on Urdu tweets. A large dataset of tweets is used, and text preprocessing techniques, feature extraction, and classification algorithms are applied.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Food Interests Analysis (FIA) model to extract the food preferences and interests of Twitter users

Mohamed

Al-Feel

Taie

2023

Labyrinth: Fayoum Journal of Science and Interdisciplinary Stud

View full text Add to dashboard Cite

Online social networks like Facebook and Twitter have played an important role in networking, disseminating information, and sharing interests and entertainment since the internet's advent into our daily lives. Twitter has significantly contributed to the analysis of its user-generated data for personalization and tasks of recommendation due to its rapid growth as a social networking platform. Twitter posts serve as an important source of information for identifying users' positive interests and creating intelligent recommendation systems. These posts provide a lot of information that may be analyzed to determine users' preferences on various topics, including food. Twitter post analysis is an interesting field of study. Several studies have studied the sentiment analysis of tweets. Also, market forecasting is a crucial issue that requires careful consideration. Business intelligence (BI) becomes an important analytical technique for assessing consumer satisfaction and market demand. Since business intelligence requires indepth analysis, sentiment analysis is the process of using natural language processing (NLP) and machine learning (ML) techniques to identify the emotional tone and attitude in text, making it useful for analyzing Twitter posts and customer reviews and identifying user preferences and market demand. As a result, it's critical to choose relevant advertisements for users at particular locations to capture their attention and generate profit. This paper develops a proposed model for a Food Interests Analysis (FIA). It collects 20,000 publicly available tweets, and then the sentiments conveyed in the tweets are captured and normalized, then clustered according to the common topic. This paper also examines the accuracy of two lexicon-based sentiment analysis approaches for tweets. Also, this study proposes an approach that combines both topic modeling and sentiment analysis (SA) by Latent Dirichlet Allocation (LDA) using the term frequency-inverse document frequency (TF-IDF) and extracting sentiment from tweets. Thus, this approach can identify the food preference categories in which users are interested.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Data obtained from diverse sources contains both useful and useless information. Therefore, the data needed to be clear before further processing [21]. So before applying any machine learning algorithms, data preparation is a crucial phase.…”

Section: Preprocessingmentioning

confidence: 99%

Food Interests Analysis (FIA) model to extract the food preferences and interests of Twitter users

Mohamed

Al-Feel

Taie

2023

Labyrinth: Fayoum Journal of Science and Interdisciplinary Stud

View full text Add to dashboard Cite

show abstract

“…Support Vector Machine: Support Vector Machine (SVM) classifiers are extensively used for brief text categorization. This categorization approach is based on the structured risk minimization concept [28][29][30][31]. Given a feature hyper-space in which each point represents a document, it generates a hyperplane that divides the data into two sets, i.e., the hyper-place divides hyperspace into two semispaces.…”

Section: Classification Techniquesmentioning

confidence: 99%

“…It's extensively utilized to solve a variety of issues, including forecasting social events, describing personality features, evaluating social crime, and so on. K Nearest Neighbor: K Nearest Neighbor (kNN), an instance-based simple machine learning classifier that uses the Euclidean equation and the value of K to determine the similarity of a class for a feature [28][29][30][31][32][33][34][35]. It determines the similarity of a feature across all documents in the training corpus.…”

Section: Classification Techniquesmentioning

confidence: 99%

Machine Learning Based Psychotic Behaviors Prediction from Facebook Status Updates

Ali¹,

Baqir²,

Sherazi³

et al. 2022

Computers, Materials &Amp; Continua

Self Cite

View full text Add to dashboard Cite

With the advent of technological advancements and the widespread Internet connectivity during the last couple of decades, social media platforms (such as Facebook, Twitter, and Instagram) have consumed a large proportion of time in our daily lives. People tend to stay alive on their social media with recent updates, as it has become the primary source of interaction within social circles. Although social media platforms offer several remarkable features but are simultaneously prone to various critical vulnerabilities. Recent studies have revealed a strong correlation between the usage of social media and associated mental health issues consequently leading to depression, anxiety, suicide commitment, and mental disorder, particularly in the young adults who have excessively spent time on social media which necessitates a thorough psychological analysis of all these platforms. This study aims to exploit machine learning techniques for the classification of psychotic issues based on Facebook status updates. In this paper, we start with depression detection in the first instance and then expand on analyzing six other psychotic issues (e.g., depression, anxiety, psychopathic deviate, hypochondria, unrealistic, and hypomania) commonly found in adults due to extreme use of social media networks. To classify the psychotic issues with the user's mental state, we have employed different Machine Learning (ML) classifiers i.e., Random Forest (RF), Support Vector Machine (SVM), Naïve Bayes (NB), and K-Nearest Neighbor (KNN). The used ML models are trained and tested by using different combinations of features selection techniques. To observe the most suitable classifiers for psychotic issue classification, a cost-benefit function (sometimes termed as 'Suitability') has been used which combines the accuracy of the model with its execution time. The experimental evidence argues that RF outperforms its competitor classifiers with the unigram feature set.

show abstract

“…Authors Pre-processing Techniques [36] Afraz Z. Syed Normalization, Segmentation [37] Afraz Z. Syed Normalization, Diacritic Omission, Tokenization, Segmentation [38] Zia Ul Rehman Tokenization, Calculate Polarity, Polarity Identification [39] Faiza Hashim POS tagging, Data cleaning [40] Kamran Amjad Tokenization, POS Tagging [41] Muhammad Yaseen Khan Normalization, Tokenization, Stop words removal, Special characters removal [42] Neelam Mukhtar Preprocessing is not performed in this paper [12] Hussain Ghulam Preprocessing is not performed in this paper [13] Neelam Mukhtar Stop words removal [14] Neelam Mukhtar Stop words removal [15] Muhammad Hassan POS Tagging, Stop words removal, Tokenization, [16] Ali Hasan Stop words removal [17] Khairullah Khan Noise removal, Tokenization, POS Tagging, Sentence boundary detection [18] Raheela Bibi Stop words removal, POS Tagging [33] Khawar Mehmood Preprocessing is not performed in this paper [19] Neelam Mukhtar Preprocessing is not performed in this paper [20] Neelam Mukhtar POS Tagging [21] Muhammad Yaseen Khan Data cleaning, Tokenization, POS Tagging [22] Daryl Essam Normalization [23] Faizan ul Mustafa Tokenization, Text cleaning, Stop words removal, Stemming [24] Asad Khattak Preprocessing is not performed in this paper [34] Halima Sadia Remove Noise, Tokenization, Stop words removal [25] Sadaf Rani Stop words removal Previous studies have proposed a broad range of techniques and methods to resolve the USA problem. This figure demonstrates the maximum techniques used in USA [46].…”

Section: Referencementioning

confidence: 99%

Urdu Sentiment Analysis: Future Extraction, Taxonomy, and Challenges

Mashooq,

Riaz,

Farooq

2022

VFAST trans. softw. eng.

View full text Add to dashboard Cite

By the newly gained attention from several research areas for the field of opinion mining, work in Sentiment Analysis (SA) has also been increased. Sentiment analysis is actually a natural language processing (NLP) method which is implemented to decide whether the data is negative, positive or neutral. This analysis can also utilized to provide most appropriate countermeasures for various issues that are connected with particular fields. It is a contextual extraction and arrangement of text which recognizes and pinpoints subjective information regarding source material and helps to understand the social sentiment of people while monitoring online conversations, comments, tweets, or information on blogs, etc. There is wide utilization of Urdu language in offering perspectives that's why the Urdu language also wants opinion mining as well. In this research, a systematic literature review on sentiment analysis of Urdu language has been performed. This SLR is focusing on explicit research questions and afterward contributions are described appropriately. The findings of the review present a taxonomy that is based on the techniques of sentiment classification. Furthermore, in this SLR, we have extracted all the preprocessing techniques that were used in these 24 papers, the most adopted algorithms by the researchers, the most implemented sentiment analysis approach, and the feature extraction techniques are also extricated. Eventually, a thorough survey is given on all these considerations. After a detailed and deep evaluation, we have computed their accuracy results for better understanding of future researchers.

show abstract

Prediction of User’s Interest Based on Urdu Tweets

Cited by 5 publications

References 17 publications

Food Interests Analysis (FIA) model to extract the food preferences and interests of Twitter users

Food Interests Analysis (FIA) model to extract the food preferences and interests of Twitter users

Machine Learning Based Psychotic Behaviors Prediction from Facebook Status Updates

Urdu Sentiment Analysis: Future Extraction, Taxonomy, and Challenges

Contact Info

Product

Resources

About