Samar Al-Saqqa

Dr. Samar Al-Saqqa


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
1 July 2018
Verified
Conference Paper
Closed access
SASamar Al-Saqqa
Samar Al-Saqqa
HAHeba Abdel-Nabi
Heba Abdel-Nabi
AAArafat Awajan
Arafat Awajan
Emotion detection in text is a research field that gained an extensive interest recently. The advancement in communication networks and the spread usage of social web is the reason of massive amount of emotions that can be extracted frequently. The extraction and analysis of such emotions provides a powerful tool in detecting and recognizing the feelings, and this provides many advantages in diverse areas. In this survey, we focused on the textual emotion detection as a task of sentiment analysis. This survey explored the latest state of art approaches for emotion detection in text, and discussed their classification according to the used techniques, the used emotional model and the different used datasets. The outcome of this paper tends to highlight the limitation and gaps of these recent works and direct the possible future research to fulfill these gaps in this increasingly developed field.

1 January 2018 in Procedia Computer Science
Verified
Journal Article
Open access
SASamar Al-Saqqa
Samar Al-Saqqa
GAGhazi Al-Naymat
Ghazi Al-Naymat
AAArafat Awajan
Arafat Awajan

1 October 2018
Verified
Conference Paper
Closed access
SASamar Al-Saqqa
Samar Al-Saqqa
NONadim Obeid
Nadim Obeid
AAArafat Awajan
Arafat Awajan
In this paper, an ensemble of machine learning classifiers approach is used to classify the sentiment polarity of Arabic text. This approach is based on the majority voting algorithm in conjunction with four classifiers, namely Naive Bayes, Support Vector Machines, Decision Trees and K-Nearest Neighbor algorithms. Four combinations of these classifiers are formed and three classifiers are chosen for each voting combination. The performance of each classifier is evaluated and compared to ensemble voting combination performance. Different experiments have been performed to evaluate unigram and bigram features. Three datasets with different sizes are used in our experiments. The first dataset contains 500 movie reviews, the second one contains 2000 Arabic tweets and the third one contains 16448 of Arabic book reviews. The experimental results show that the ensemble of the classifiers comparatively gives better results than individual classifiers. They also reveal that the support vector machine classifier outperforms the other individual classifiers. Moreover, the results of the bigram feature are better than the results of the unigram feature.

1 October 2015
Verified
Conference Paper
Closed access
DQDana A. Al Qudah
Dana A. Al Qudah
Alexandra I. CristeaAlexandra I. Cristea
Alexandra I. Cristea
SBSuncica Hadzidedic Bazdarevic
Suncica Hadzidedic Bazdarevic
SASamar Al-Saqqa
Samar Al-Saqqa
ARAli Rodan
Ali Rodan
WYWei Yang
Wei Yang
Personalized e-advertising is the art of attracting users' attention by correlating to their tastes and interests. The evolving research of adaptive hypermedia with its techniques and theories contributed to the personalization field. This paper reports the case study of "My Ads", an adaptive e-advertisement delivery system that is based on a new theoretical framework, to evaluate users' acceptance of personalized ads. The results indicated that the implemented features within the system contributed to an enhanced experience through the exposure to different personalization methods and the appealing ideas of the system.

2 May 2026 in Computation
Verified
Journal Article
Open access
PDF file
NSNajem N. Sirhan
Najem N. Sirhan
RARiyad Alrousan
Riyad Alrousan
SASamar Al-Saqqa
Samar Al-Saqqa
FHFaten Hamad
Faten Hamad
Zaid KhrisatZaid Khrisat
Zaid Khrisat
Accurate short-horizon downlink throughput prediction is essential for automation in high-density 5G deployments (e.g., stadiums and events), where user load, scheduling decisions, and interference conditions change rapidly and produce highly variable user-perceived rates. This paper benchmarks lightweight regression models for per-user throughput prediction from readily available radio access network (RAN) key performance indicators (KPIs) and studies a risk-aware extension that augments point forecasts with calibrated uncertainty and an abstention (deferral) rule. Experiments use a strictly time-ordered train/calibration/test protocol on the Liverpool 5G High-Density Demand (L5GHDD) dataset. The target is strongly zero-inflated (about 62% of samples at 0 Mbps) and heavy-tailed, creating regimes where average-error optimization can mask rare but operationally important bursts. In the point-prediction benchmark, the best model is a tuned two-stage support vector regressor with a mean absolute error (MAE) of 0.452 Mbps, while the strongest single-stage model attains a weighted mean absolute percentage error (WMAPE) of 56.200%. For uncertainty quantification, we compare standard split conformal prediction against two input-adaptive alternatives. Constant-width split conformal attains 88.900% marginal coverage for a nominal 90% target with an average interval width of 2.288 Mbps, but width-based deferral is degenerate because all intervals have the same size. Variable-length conformal intervals preserve near-nominal coverage (91.100%) while producing informative width variation: normalized conformal reduces the average width to 1.344 Mbps, and conformalized quantile regression reduces it to 0.641 Mbps. At a deferral threshold of 1.500 Mbps, constant-width conformal defers all samples, whereas normalized conformal still acts on 61.200% of samples with selective MAE 0.219 Mbps. These results show that input-adaptive uncertainty is necessary for meaningful selective prediction in heteroscedastic 5G throughput dynamics.

1 October 2015
Verified
Conference Paper
Closed access
DQDana A. Al Qudah
Dana A. Al Qudah
Alexandra I. CristeaAlexandra I. Cristea
Alexandra I. Cristea
SBSuncica Hadzidedic Bazdarevic
Suncica Hadzidedic Bazdarevic
SASamar Al-Saqqa
Samar Al-Saqqa
RARizik M. H. Al-Sayyad
Rizik M. H. Al-Sayyad
The art of personalized e-advertising relies in attracting a user attention to the recommended product, as it relates to their taste, interest and data. Whilst in practice, companies attempt various forms of personalization, research of e-advertising is rare, and seldom routed in solid theory. Adaptive hypermedia (AH) techniques have contributed to the development of personalized tools for adaptive content delivery, mostly in educational domain. This study explores the use of these theories and techniques in a specific field -- adaptive e-advertisements, via implementing and evaluating an adaptive e-advertisement system called "MyAds". The novelty of this approach relies in a systematic design, implementation and evaluation based on an adaptive hypermedia taxonomy-. In particular, this paper reports on a case study, which investigated users' perceptions' on the proposed system MyAds and the reflection of the acceptance level of the users. The results from both implicit and explicit feedback indicated that users found MyAds acceptable and agreed that the implemented AH features within the system contributed to an enhanced experience through the exposure to different personalization methods. Appealing ideas of the system were ease of use, personalization and diversity in a non-intrusive way.