Socio-semantic conversational information access

This thesis lies broadly in the field of intelligent information access, primarily at the intersection of language processing, user modeling and web based socio-informatics systems. The main contributions revolve around developing this integrated conversational recommendation framework, combining data and information models with community network and interactions to leverage multi-modal information access. This work has been in uenced by a number of fields such as Information Retrieval and Extraction, Case based Reasoning, User Modeling and Adaptation, and Socio-Technical Systems.;We have developed a real time conversational information access community agent that leverages the community knowledge by pushing relevant recommendations to users of the community. The recommendations are delivered in the form of web resources, past conversation and people to connect to. The information agent (cobot, for community/collaborative bot) monitors the community conversations, and is 'aware' of users' preferences by implicitly capturing their short term and long term knowledge models from conversations. The agent leverages from health and medical domain knowledge to extract concepts, associations and relationships between concepts, formulates queries for semantic search and ultimately provides socio-semantic recommendations in the conversation after applying various relevance filters to the candidate results. The agent also takes into account users' verbal intentions in conversations while making recommendation decision.;One of the goals of this thesis is to develop an innovative approach to delivering relevant information using a combination of social networking, information aggregation, semantic search and recommendation techniques. The idea is to facilitate timely and relevant social information access by mixing past community specific conversational knowledge and web information access to recommend and connect users with relevant information.;With an explosion in proliferation of user-generated content, the productivity of search is decreasing and quality of readily available online content is deteriorating. There is an increasing need for intelligent assistants that can understand user interactions in the social context for better addressing the problem solving needs of the user. Cobot models user utterances in conversations to proactively target the community for exchange of questions and answers in conversations. We envision a system that encourages user engagement and participation by prompting questions and asking to suggest answers based on user's knowledge and activity levels.;One problem with social information systems is the noise-signal ratio. This ratio becomes high due to informal nature of the language in conversations in communities which hinders relevant recommendations. One solution is to normalize the community conversations to extract meaningful representations using conceptual knowledge coming from socially generated tags or knowledge from an ontology. This underlying conceptual base for consumption and participation drives internal knowledge representation for the socio-semantic system.;Language and interaction creates usable memories, useful for making decisions about what actions to take and what information to retain. Cobot leverages these interactions to maintain users' episodic and long term semantic models. The agent analyzes these memory structures to match and recommend users in conversations by matching with the contextual information need. The social feedback on the recommendations is registered in the system for the algorithms to promote community preferred, contextually relevant resources.;The nodes of the semantic memory are frequent concepts extracted from user's interactions. The concepts are connected with associations that develop when concepts co-occur frequently. Over a period of time when the user participates in more interactions, new concepts are added to the semantic memory. Different conversational facets are matched with episodic memories and a spreading activation search on the semantic net is performed for generating the top candidate user recommendations for the conversation. The activation is spread to the neighboring nodes proportional to the weight of each connecting association in the semantic net. There are several parameters in the system that can be learnt based on activity of users. Parameters for episodic memory window size, semantic memory learning and unlearning rates, concept co-occurrences and feedback strengths for associations are initially set heuristically and can be fine-tuned to suit individual users.;The tying themes in this thesis revolve around informational and social aspects of a unified information access architecture that integrates semantic extraction and indexing with user modeling and recommendations.