Tanu Sharma
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tanu Sharma has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Kamaldeep Kaur
USICT, Guru Gobind Singh Indraprastha University
4 shared publications - Aarti Yadav
Teerthanker Mahaveer Dental College and Research Centre, Moradabad, India
1 shared publication J.S. Yadav
Department of Zoology, Kurukshetra University, Kurukshetra 136 119, Haryana, India Fax No. 90-1744-20277
1 shared publication
Latest Publications
- 15 November 2024
- Published by SAGE Publications in Intelligent Decision Technologies
- Vol. 19 (2) , 1123-1141
A method for product ranking based on aspect based sentiment analysis of online reviews
The plethora of online reviews available on the internet has great insights about various products or entities. However, selecting or recommending a product by sifting through these reviews is a tedious and time consuming task. Sentiment analysis of such reviews helps understand the pros or cons of the product. In recent years researchers and industry people have leveraged such reviews to rank or recommend the products to new users. Ranking or recommending products using text reviews is a challenging task. In this study, we propose a framework to get a ranking of products using aspect-based sentiment analysis (ABSA). ABSA is a fine-grained sentiment analysis task that is useful for extracting opinions about the different aspects of a product. To facilitate automated ABSA, a novel approach for aspect sentiment classification is proposed in this study. Further to rank the products based on aspect-specific performance, a framework is developed using Multi-criteria decision-making (MCDM) techniques. A case study is performed in the automobile domain to rank various cars using the ABSA approach. To validate the effectiveness of the proposed approach, the ranking results are compared with the numeric ratings available for various aspects of the car. The experimental results show that the ranking obtained by the proposed approach matches the numerical ratings. Therefore, the car selection problem or recommendation of cars in the automobile domain can be effectively handled using the proposed framework.
- 15 November 2024
- Published by SAGE Publications in Intelligent Decision Technologies
- Vol. 19 (2) , 1123-1141
A method for product ranking based on aspect based sentiment analysis of online reviews
The plethora of online reviews available on the internet has great insights about various products or entities. However, selecting or recommending a product by sifting through these reviews is a tedious and time consuming task. Sentiment analysis of such reviews helps understand the pros or cons of the product. In recent years researchers and industry people have leveraged such reviews to rank or recommend the products to new users. Ranking or recommending products using text reviews is a challenging task. In this study, we propose a framework to get a ranking of products using aspect-based sentiment analysis (ABSA). ABSA is a fine-grained sentiment analysis task that is useful for extracting opinions about the different aspects of a product. To facilitate automated ABSA, a novel approach for aspect sentiment classification is proposed in this study. Further to rank the products based on aspect-specific performance, a framework is developed using Multi-criteria decision-making (MCDM) techniques. A case study is performed in the automobile domain to rank various cars using the ABSA approach. To validate the effectiveness of the proposed approach, the ranking results are compared with the numeric ratings available for various aspects of the car. The experimental results show that the ranking obtained by the proposed approach matches the numerical ratings. Therefore, the car selection problem or recommendation of cars in the automobile domain can be effectively handled using the proposed framework.
- 15 November 2023
- Published by Springer Nature
- p. 317-328
An Equilibrium Optimizer-Based Ensemble for Aspect-Level Sentiment Classification
- 15 November 2023
- Published by Springer Nature
- p. 317-328
An Equilibrium Optimizer-Based Ensemble for Aspect-Level Sentiment Classification
- 25 March 2023
- Published by Springer Nature
- p. 861-872
An Ensemble Approach for Aspect-Level Sentiment Classification Using Deep Learning Methods
- 25 March 2023
- Published by Springer Nature
- p. 861-872
An Ensemble Approach for Aspect-Level Sentiment Classification Using Deep Learning Methods
- Open Access
- 9 November 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (22) , 10542
Benchmarking Deep Learning Methods for Aspect Level Sentiment Classification
With the advancements in processing units and easy availability of cloud-based GPU servers, many deep learning-based methods have been proposed for Aspect Level Sentiment Classification (ALSC) literature. With this increase in the number of deep learning methods proposed in ALSC literature, it has become difficult to ascertain the performance difference of one method over the other. To this end, our study provides a statistical comparison of the performance of 35 recent deep learning methods with respect to three performance metrics-Accuracy, Macro F1 score, and Time. The methods are evaluated for eight benchmark datasets. In this study, the statistical comparison is based on Friedman, Nemenyi, and Wilcoxon tests. As per the results of statistical tests, the top-ranking methods could not significantly outperform several other methods in terms of Accuracy and Macro F1 score and performed poorly on-time metric. However, the time taken by any method is crucial to analyze the overall performance. Thus, this study aids the selection of the Deep Learning method, which maximizes the accuracy and Macro F1 score and takes minimal time. Our study also establishes a framework for validating the performance of new and alternate methods in ALSC that can be helpful for researchers and practitioners working in this area.
- 9 November 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (22) , 10542
Open AccessBenchmarking Deep Learning Methods for Aspect Level Sentiment Classification
With the advancements in processing units and easy availability of cloud-based GPU servers, many deep learning-based methods have been proposed for Aspect Level Sentiment Classification (ALSC) literature. With this increase in the number of deep learning methods proposed in ALSC literature, it has become difficult to ascertain the performance difference of one method over the other. To this end, our study provides a statistical comparison of the performance of 35 recent deep learning methods with respect to three performance metrics-Accuracy, Macro F1 score, and Time. The methods are evaluated for eight benchmark datasets. In this study, the statistical comparison is based on Friedman, Nemenyi, and Wilcoxon tests. As per the results of statistical tests, the top-ranking methods could not significantly outperform several other methods in terms of Accuracy and Macro F1 score and performed poorly on-time metric. However, the time taken by any method is crucial to analyze the overall performance. Thus, this study aids the selection of the Deep Learning method, which maximizes the accuracy and Macro F1 score and takes minimal time. Our study also establishes a framework for validating the performance of new and alternate methods in ALSC that can be helpful for researchers and practitioners working in this area.
- 4 September 2001
- Published by Kamla Raj Enterprises in International Journal of Human Genetics
- Vol. 1 (3) , 195-202
Chromosome Damage in Lymphocytes of Stainless Steel Welders
Genotoxic effect of welding fumes generated by Manual Metal Arc (MMA), Metal Inert Gas (MIG) and Oxyacetylene welding on the lymphocytes of 75 welders, 25 from each group and equal number of healthy matched controls, was investigated by studying Mitotic Index (MI), Chromosome Aberrations (CAs), Sister Chromatid Exchanges (SCEs), and Satellite Associations (SAs) The MI showed significant increase in all the three groups (4.25 - 7.66, 4.35 - 7.63, 4.63 - 7.54). The background frequency for CAs was normal (0.88, 0.84, 0.92). It significantly increased in all the three groups (4.68, 3.84, 2.96). Among controls only chromatid gaps and breaks were observed, while chromosome type aberrations could not be seen. Among exposed samples both chromatid type viz. gaps, breaks and isochromatid exchanges and chromosome type aberrations viz. dicentrics, rings, acentric fragments, translocations, chromosome gaps, chromosome breaks and diplochromosomes were observed. The frequency of SCEs also increased (3.98 - 7.84, 4.16 - 4.72, 4.57 - 6.43). However, the increase was significant in group-1 and group-3 welders only. Synergistic effect of smoking and alcohol was noticed in both CAs and SCEs, the frequencies being the highest in smokeralcoholics and lowest in non smoker - non alcoholics. The CAs and SCEs also revealed correlation with the duration of exposure. The frequencies of SAs also depicted significant increase (4.8 - 13.8, 5.64 - 11.48, 5.56 - 9.28). The D-G type of associations outnumbered all other types. It is concluded that the welding fumes, containing chromium (Cr VI) and nickel, cause considerable chromosomal damage. The welders, in their occupational settings are prone to high genetic risk.
- 4 September 2001
- Published by Kamla Raj Enterprises in International Journal of Human Genetics
- Vol. 1 (3) , 195-202
Chromosome Damage in Lymphocytes of Stainless Steel Welders
Genotoxic effect of welding fumes generated by Manual Metal Arc (MMA), Metal Inert Gas (MIG) and Oxyacetylene welding on the lymphocytes of 75 welders, 25 from each group and equal number of healthy matched controls, was investigated by studying Mitotic Index (MI), Chromosome Aberrations (CAs), Sister Chromatid Exchanges (SCEs), and Satellite Associations (SAs) The MI showed significant increase in all the three groups (4.25 - 7.66, 4.35 - 7.63, 4.63 - 7.54). The background frequency for CAs was normal (0.88, 0.84, 0.92). It significantly increased in all the three groups (4.68, 3.84, 2.96). Among controls only chromatid gaps and breaks were observed, while chromosome type aberrations could not be seen. Among exposed samples both chromatid type viz. gaps, breaks and isochromatid exchanges and chromosome type aberrations viz. dicentrics, rings, acentric fragments, translocations, chromosome gaps, chromosome breaks and diplochromosomes were observed. The frequency of SCEs also increased (3.98 - 7.84, 4.16 - 4.72, 4.57 - 6.43). However, the increase was significant in group-1 and group-3 welders only. Synergistic effect of smoking and alcohol was noticed in both CAs and SCEs, the frequencies being the highest in smokeralcoholics and lowest in non smoker - non alcoholics. The CAs and SCEs also revealed correlation with the duration of exposure. The frequencies of SAs also depicted significant increase (4.8 - 13.8, 5.64 - 11.48, 5.56 - 9.28). The D-G type of associations outnumbered all other types. It is concluded that the welding fumes, containing chromium (Cr VI) and nickel, cause considerable chromosomal damage. The welders, in their occupational settings are prone to high genetic risk.