Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
5 results
Search Results
Item KCe_Dalab@maponsms-Fire2018: Effective word and character-based features for multilingual author profiling(CEUR-WS ceurws@sunsite.informatik.rwth-aachen.de, 2018) Sharmila Devi, V.; Subramanian, S.; Ravikumar, G.; Anand Kumar, M.This paper illustrates the work on identification of gender and age-group in Multilingual Author Profiling on SMS messages (MAPonSMS) shared task conducted in the Forum for Information Retrieval and Evaluation (FIRE 2018). To develop the Multilingual Author profiling system, the organizers released the training corpus which includes multilingual (Roman Urdu and English) SMS messages and its corresponding profiles. In gender identification, a profile may be either male or female. The author's age-group fall into one of the three categories: 15-19, 20-24, 25-xx. We have developed the author profiling system 1 using the word and character-based Term Frequency & Inverse Document Frequency (TFIDF) features and classify with Support Vector Machine classifier. The proposed system achieved the State-of-Art performance in the multilingual author profiling on SMS task. The accuracy obtained for identification of age-group is 65% and for gender, it is 87%. The performance is also evaluated jointly where the accuracy gained is 57%. We also experimented with the system by changing different parameters and report the cross-validation accuracy. © 2018 CEUR-WS. All Rights Reserved.Item KCE DALab-APDA@FIRE2019: Author profiling and deception detection in Arabic using weighted embedding(CEUR-WS ceurws@sunsite.informatik.rwth-aachen.de, 2019) Sharmila Devi, V.; Subramanian, S.; Ravikumar, G.; Anand Kumar, M.A.This paper explaining the work submitted on Author Pro- filing and Deception Detection in Arabic Tweets shared task organized at the Forum for Information Retrieval Evaluation (FIRE) 2019. The first task Author profiling illustrates identifying the categories of au- thors based on the Arabic tweets. In the second task, the aim is to Detect deception in Arabic for two genres such as Twitter and News. Deception detection means that the automatic way of identifying false messages in the text content on social network or news. For each task, we have submitted three different systems. For submission 1, we have used the Term Frequency and Inverse Document Frequency (TFIDF) based Support Vector Machine classification and in submission 2, we have used fastText classifier. For submission 3, we have proposed a low dimensional weighted document embedding (TFIDF + Word embedding) with SVM classification. We have attained second place in the Deception detection and third in Author profiling. The performance difference between the top team results and the submitted runs are only 3.34% for Author pro- filing and 1.16% for Deception detection. © Copyright 2019 for this paper by its authors.Item Electroslag remelting experiments have been carried out on En 24 steel using two slag compositions in indigeneously constructed 350 KVA DC and 50 KVA AC ESR units. Detailed quantitative characterisation of the inclusions of different types has been carried out using Quantimet Image Analyser. The inclusion content in terms of volume fraction and density (No/mm2) and their size distribution in the refined ingot and the unrefined steel have been assessed. The chemical composition of selected inclusions has been established by electron probe microanalyser (EPMA). These studies are supplemented by scanning electron microscopy on typical fractured specimens. The present study shows that the DC reverse polarity mode of melting using a slag with higher silica content (10 wt%) offers the best conditions with particular reference to removal of inclusions and modification of inclusion morphology as compared to the ingots produced by DC straight polarity and AC modes of melting.(Studies on inclusion characterization in electroslag refined En24 steel) Udupa, K.R.; Subramanian, S.; Sastry, D.H.; Iyengar, G.N.K.1994Item Solar active ZnO–Eu2O3 for energy and environmental applications(Elsevier Ltd, 2020) Subramanian, S.; Kumaravel, K.; K, K.; Bhat, D.K.; Iyer Sathiyanarayanan, K.; Swaminathan, M.ZnO–Eu2O3 nanocomposite was fabricated by a simple hydrothermal route. This material forms a potential class of photocatalysts in which the increased absorption behaviour in ZnO–Eu2O3 is expected to couple with the existing characteristics of Eu2O3 and ZnO materials. ZnO–Eu2O3 was characterized using surface analytical (SEM, EDS, HR-TEM, AFM, XRD) and spectroscopic techniques (XPS, DRS,PL). From the XRD patterns, formation of well-crystallized cubic Eu2O3 and hexagonal wurtzite phase of ZnO were inferred. Presence of nanoflake like structure with hexagonal ZnO and cubical Eu2O3 is shown by SEM pictures. ZnO–Eu2O3 possesses higher UV and visible absorption than Eu2O3 and ZnO. ZnO–Eu2O3 produces larger methanol oxidation current indicating its anodic catalytic efficiency in direct methanol fuel cells (DMFCs). This reveals higher electrocatalytic activity of ZnO–Eu2O3 than ZnO. It is observed that at ?1.6 V, cathodic current density (ipc) of ZnO–Eu2O3 (?103.17 mA cm?2) for Hydrogen evolution reaction (HER) is more than five times of ZnO (?18.19 mA cm?2) and the hydrogen evolved with ZnO–Eu2O3is 15.6 mL, which is higher than that of ZnO (6.8 mL). This indicates the superior catalytic property of ZnO–Eu2O3 in water splitting. This catalyst exhibited higher catalytic activity of 99.2% in the photodegradation of Rhodamine B (Rh-B) with natural sunlight in 75 min under neutral pH, whereas Eu2O3 and ZnO produced 60 and 82% degradations in the same time. Degradation quantum efficiency by ZnO–Eu2O3 is larger than ZnO and Eu2O3. ZnO–Eu2O3 was stable and reusable. The multifunctionality of this catalyst makes it suitable for energy and environmental applications. © 2020 Elsevier B.V.Item The Effect of Phrase Vector Embedding in Explainable Hierarchical Attention-Based Tamil Code-Mixed Hate Speech and Intent Detection(Institute of Electrical and Electronics Engineers Inc., 2024) Sharmila Devi, V.S.; Subramanian, S.; Anand Kumar, A.K.The substantial growth in social media users has led to a significant increase in code-mixed content on social media platforms. Millions of users on these platforms upload pictures and videos and post comments regarding their recent or exciting activities. Responding to this uploaded content, a few users occasionally use offensive language to insult others or specific groups. Social media platforms encounter challenges identifying and removing hate speech and objectionable content in various languages. Hate speech, in its general sense, refers to harmful posts directed at individuals or groups based on factors such as their sexuality, religion, community affiliation, disability, and others. Typically, offensive language is directly or indirectly utilized in hate speech posts to insult someone, causing psychological distress to users. In light of this, we propose developing a system to automatically block, remove, or report posts written in code-mixed Tamil containing hate speech. We have gathered code-mixed Tamil comments from Twitter and the Helo App, categorizing them as hate speech and classifying their intent. We have identified three categories of hate speech intent, namely Targeted Individual (TI), Targeted Group (TG), and Others (O). The Targeted Individual (TI) class encompasses posts aimed at a specific individual target. At the same time, the Targeted Group (TG) category primarily focuses on identifying people based on their religion, community, gender, and other characteristics. The Others (O) category encompasses untargeted offensive posts and other posts containing offensive language. In this context, we propose using a phrase-based, Explainable Hierarchical Attention model for hate speech detection. The results demonstrate that the proposed method is more effective in identifying and explaining hate speech and offensive language in social media posts. © 2013 IEEE.