Ummu Hani’ Hair Zaki

Ummu Hani’ Hair Zaki

Auto-generated profile, based on publicly available information

Ummu Hani’ Hair Zaki

Department of Applied Computing, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Johor, Malaysia

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2017
Verified
Conference Paper
Closed access
UZUmmu Hani' Hair Zaki
Ummu Hani' Hair Zaki
RIRoliana Ibrahim
Roliana Ibrahim
SHShahliza Abd Halim
Shahliza Abd Halim
KKKhairul Anwar Mohamed Khaidzir
Khairul Anwar Mohamed Khaidzir
TYTakeru Yokoi
Takeru Yokoi
The growing utilization of Web 2.0 leads us to extract, transform, load, and analyze enormously and sizably voluminous amount of structured and unstructured data, at a speedy pace, mentioned to as `Big Data'. With the help of collected public opinion from social media, users are transforming themselves into a social sensor. Data produced by social media is believed can be important in understanding the public's reactions and feelings. Particularly for disaster management, finding posts that indicate a situation of dissatisfaction, danger or worrying may prove critical. Consequently, a systematic classification is genuinely helpful in processing these posts and classify them into sentiment polarity and aspect-based classification that will benefit diverse agencies such as non-government or government in managing such crisis situations. However, there is less work of other researchers in developing big data application using a systematic method such as methodology. Distinctly, in disaster management system that exploits sentiment analysis. Based on ATHENA project, this work extends the Crisis Information Processing Centre component by using supervised learning technique of machine learning approach with the incorporation of RUP/SOMA methodology.


1 November 2017
Verified
Conference Paper
Closed access
AYAlireza Yousefpour
Alireza Yousefpour
HHHaza Nuzly Abdul Hamed
Haza Nuzly Abdul Hamed
UZUmmu Hani' Hair Zaki
Ummu Hani' Hair Zaki
KKKhairul Anwar Mohamed Khaidzir
Khairul Anwar Mohamed Khaidzir
The complexity of an optimal feature subset selection for sentiment classification problem grows exponentially based on the number of features. The paper aims to enhance the selection of feature subset in high-dimensional feature space based on filter approach. Filter-based methods evaluate features relevance by considering only at the properties of the data. The score of the feature is calculated, then low-scoring features will be removed. In most feature selection methods, the selection of a feature subset is based on the feature space while the model hypothesis space is ignored. To assess the relevance of features, a feature ranking by distance measure is conducted to minimize intra-class and maximize inter-class distance. A filter method based on distribution and dispersion of features on feature space namely mutual standard deviation is proposed. Wide ranges of comparative experiments are performed on two widely used datasets, namely, movie, and book review dataset, in sentiment analysis. The results showed that proposed feature ranking method outperforms the other baseline methods regarding accuracy.

25 February 2024 in Baghdad Science Journal
Verified
Journal Article
Open access
PDF file
UZUmmu Hani’ Hair Zaki
Ummu Hani’ Hair Zaki
RIRoliana Ibrahim
Roliana Ibrahim
SHShahliza Abd Halim
Shahliza Abd Halim
IKIzyan Izzati Kamsani
Izyan Izzati Kamsani
تستخدم معظم الشركات بيانات وسائل التواصل الاجتماعي للأعمال. يقوم تحليل المشاعر تلقائيًا بجمع التحليلات وتلخيص هذا النوع من البيانات. من الصعب إدارة بيانات وسائل التواصل الاجتماعي غير المنظمة. حيث تمثل البيانات المزعجة او غير متناسقة تحديًا لتحليل المشاعر. نظرًا لأن أكثر من 50٪ من عملية تحليل المشاعر هي معالجة مسبقة للبيانات، فإن معالجة بيانات الوسائط الاجتماعية الضخمة تمثل تحديًا أيضًا. إذا تم إجراء المعالجة المسبقة بشكل صحيح، فقد تتحسن دقة البيانات. أيضًا، يعتمد سير العمل في تحليل المشاعر بشكل كبير. نظرًا لعدم وجود تقنية معالجة مسبقة تعمل بشكل جيد في جميع المواقف أو مع جميع مصادر البيانات، فإن اختيار أهم المصادر أمر بالغ الأهمية. تحديد الأولويات هو أسلوب ممتاز لاختيار الأكثر أهمية.باعتبارها إحدى طرق اتخاذ القرار متعدد المعايير (MCDM)، تُفضل عملية التحليل الهرمي (AHP) التعامل مع تحديات صنع القرار المعقدة باستخدام عدة معايير. تم استخدام درجات نسبة الاتساق (CR) لفحص المقارنات الزوجية لتقييم AHP. استخدمت هذه الدراسة مقياسين للحصول على الحكم الأكثر اتساقًا. أولاً، مقياس حكم Saaty (SS)، ثم المقياس المتوازن المعمم (GBS). لقد تم...

15 December 2019 in International Journal of Advanced Trends in Computer Science and Engineering
Verified
Journal Article
Closed access
UZUmmu Hani’ Hair Zaki
Ummu Hani’ Hair Zaki