Moumita Basu

Retrieving Information from Multiple Sources

The Web has several information sources on which an ongoing event is discussed. To get a complete picture of the event, it is important to retrieve information from multiple sources. We propose a novel neural network based model which integrates the embeddings from multiple sources, and thus retrieves information from them jointly, %all the sources together, as opposed to combining multiple retrieval results. The importance of the proposed model is that no document-aligned comparable data is needed. Experiments on posts related to a particular event from three different sources - Facebook, Twitter and WhatsApp - exhibit the efficacy of the proposed model.

Automatic Matching of Resource Needs and Availabilities in Microblogs for Post-Disaster Relief

During a disaster event, it is essential to know about needs and availabilities of different types of resources, for coordinating relief operations. Microblogging sites are frequently used for aiding post-disaster relief operations, and there have been prior attempts to identify tweets that inform about resource needs and availabilities (termed as need-tweets and availability-tweets respectively). However, there has not been much attempt to effectively utilise such tweets. We introduce the problem of automatically matching need-tweets with appropriate availability-tweets, which is practically important for coordination of post-disaster relief operations. We also experiment with several methodologies for automatically matching need-tweets and availability-tweets.

Identifying Post-Disaster Resource Needs and Availabilities from Microblogs

Microblogging sites like Twitter are increasingly being used for aiding post-disaster relief operations. In such situations, identifying needs and availabilities of various types of resources is critical for effective coordination of the relief operations. We focus on the problem of automatically identifying tweets that inform about needs and availabilities of resources, termed as need-tweets and availability-tweets respectively. Traditionally, pattern matching techniques are adopted to identify such tweets. In this work, we present novel retrieval methodologies, based on word embeddings, for automatically identifying need-tweets and availability-tweets. Experiments over tweets posted during two recent disaster events show that the proposed methodologies outperform prior pattern-matching techniques.

Utilizing Online Social Media for Disaster Relief: Practical Challenges in Retrieval

In recent years, several disaster events (e.g., earthquakes in Nepal-India and Italy, terror attacks in Paris and Brussels) have proven the crucial role of Online Social Media (OSM) in providing actionable situational information. However, in such media, the crucial information is typically obscured by a lot of insignificant information (e.g., personal opinions, prayers for victims). Moreover, when time is critical, owing to the rapid speed and huge volume of microblogs, it is infeasible for human subjects to go through all the tweets posted. Hence, automated IR methods are needed to extract the relevant information from the deluge of posts. Though several methodologies have been developed for tasks like classification, summarization, etc. of social media data posted during disasters [5], there are still several research challenges that need to be addressed for effectively utilising social media data (e.g., microblogs) for aiding disaster relief operations

Medical Requirements During a Natural Disaster: A Case Study on WhatsApp Chats Among Medical Personnel During the 2015 Nepal Earthquake.

OBJECTIVE The objective of this study was to explore a log of WhatsApp messages exchanged among members of the health care group Doctors For You (DFY) while they were providing medical relief in the aftermath of the Nepal earthquake in April 2015. Our motivation was to identify medical resource requirements during a disaster in order to help government agencies and other responding organizations to be better prepared in any upcoming disaster. METHODS A large set of WhatsApp (WhatsApp Inc, Mountain View, CA) messages exchanged among DFY members during the Nepal earthquake was collected and analyzed to identify the medical resource requirements during different phases of relief operations. RESULTS The study revealed detailed phase-wise requirements for various types of medical resources, including medicines, medical equipment, and medical personnel. The data also reflected some of the problems faced by the medical relief workers in the earthquake-affected region. CONCLUSIONS The insights from this study may help not only the Nepalese government, but also authorities in other earthquake-prone regions of the world to better prepare for similar disasters in the future. Moreover, real-time analysis of such online data during a disaster would aid decision-makers in dynamically formulating resource-mapping strategies. (Disaster Med Public Health Preparedness. 2017;11:652-655).

Microblog Retrieval During Disasters: Comparative Evaluation of IR Methodologies

Microblogging sites are important sources of situational information during any natural or man-made disasters. Hence, it is important to design and test Information Retrieval (IR) systems that retrieve information from microblogs during disasters. With this perspective, a track was organized at the 8th meeting of Forum for Information Retrieval Evaluation (FIRE) 2016, focused on microblog retrieval during disaster events. A collection of about 50,000 microblogs posted during the Nepal Earthquake in April 2015 was released, along with a set of seven pragmatic information needs during a disaster situation. The task was to retrieve microblogs relevant to these information needs. Ten teams participated in the task, and fifteen runs were submitted. Evaluation of the performances of various microblog retrieval methodologies, as submitted by the participants, revealed several challenges associated with microblog retrieval. In this chapter, we describe our experience in organizing the FIRE track on microblog retrieval during disaster events. Additionally, we propose two novel methodologies for the said task, which perform better than all the methodologies submitted to the FIRE track.