No abstract

The architecture, engineering, and construction (AEC) industry has seen a significant rise in the adoption of Building Information Modeling (BIM) in the last few years. BIM software have launched with numerous robust capabilities and features to satisfy the ever-demanding needs of the AEC industry. Various factors are associated with the selection of BIM software depending on a company’s requirements and constraints. BIM software selection is a daunting process as most AEC industries are unaware of the factors to consider when making this important decision. This study focuses on identifying the critical success factors (CSFs) and their interrelationship for efficient BIM software selection. For this research, a questionnaire was developed and disseminated in two stages in India, the United States of America (U.S.A.), Germany, and the United Kingdom (U.K.). In the first stage, a total of twenty-six identified CSFs were analyzed with the factor comparison method (FCM) to identify the top fifteen CSFs. Subsequently, the identified top fifteen CSFs were further assessed by implementing Fuzzy DEMATEL to categorize them into cause-and-effect groups based on respective influence strength, depicted with a causal diagram. Out of fifteen CSFs, five and ten factors were grouped into the cause group and effect group for BIM software selection, respectively. The most important factors were identified as software functionality, BIM adoption strategies and processes, interoperability, staff competencies, BIM standards and regional regulations. The outcome of this research can help BIM user companies improve their BIM software selection framework and decision-making process during purchasing software.

This paper presents online hate speech as a societal and computational challenge. Offensive content detection in social media is considered as a multilingual, multi-level, multi-class classification problem for three Indo-European languages. This research problem is offered to the community through the HASOC shared task. HASOC intends to stimulate research and development in hate speech recognition across different languages. Three datasets (in English, German, and Hindi) were developed from Twitter and Facebook, and made available. This paper describes the creation of the multilingual datasets and the annotation method. We will present the numerous approaches based on traditional classifiers, deep neural models, and transfer learning models, along with features used for the classification. Results show that the best classifier for the binary classification might not perform best in the multi-class classification, and the performance of the same classifier varies across the languages. Overall, transfer learning models such as BERT, and deep neural models based on LSTMs and CNNs perform similar but better than traditional classifiers such as SVM. We will conclude the discussion with a list of issues that needs to be addressed for future datasets.

This paper presents the participation of team DA-LD-Hildesheim of Information Retrieval and Language Processing lab at DA-IICT, India in Semeval-19 OffenEval track. The aim of this shared task is to identify offensive content at fined-grained level granularity. The task is divided into three sub-tasks. The system is required to check whether social media posts contain any offensive or profane content or not, targeted or untargeted towards any entity and classifying targeted posts into the individual, group or other categories. Social media posts suffer from data sparsity problem, Therefore, the distributed word representation technique is chosen over the Bag-of-Words for the text representation. Since limited labeled data was available for the training, pre-trained word vectors are used and fine-tuned on this classification task. Various deep learning models based on LSTM, Bidirectional LSTM, CNN, and Stacked CNN are used for the classification. It has been observed that labeled data was highly affected with class imbalance and our technique to handle the class-balance was not effective, in fact performance was degraded in some of the runs. Macro F1 score is used as a primary evaluation metric for the performance. Our System achieves Macro F1 score = 0.7833 in sub-task A, 0.6456 in the sub-task B and 0.5533 in the sub-task C.

No abstract