Abstract Internet users are increasingly inclined to contribute comments to online news articles,... more Abstract Internet users are increasingly inclined to contribute comments to online news articles, videos, product reviews, and blogs. The most common interface for comments is a list, sorted by time of entry or by binary ratings. It is widely recognized that such lists do not scale well and can lead to" cyberpolarization," which serves to reinforce extreme opinions.
Abstract Standard Sentiment Analysis applies Natural Language Processing methods to assess an" ap... more Abstract Standard Sentiment Analysis applies Natural Language Processing methods to assess an" approval" value of a given text, categorizing it into" negative"," neutral", or" positive" or on a linear scale. Sentiment Analysis can be used to infer ratings values for users based on textual reviews of items such as books, films, or products. We propose an approach to generalizing the concept to multiple dimensions to estimate user ratings along multiple axes such as" service"," price" and" value".
Abstract Many practitioners currently use rules of thumb to price tasks on online labor markets. ... more Abstract Many practitioners currently use rules of thumb to price tasks on online labor markets. Incorrect pricing leads to task starvation or inefficient use of capital. Formal pricing policies can address these challenges. In this paper we argue that a pricing policy can be based on the trade-off between price and desired completion time. We show how this duality can lead to a better pricing policy for tasks in online labor markets. This paper makes three contributions.
ABSTRACT In order to seamlessly integrate a human computation component (eg, Amazon Mechanical Tu... more ABSTRACT In order to seamlessly integrate a human computation component (eg, Amazon Mechanical Turk) within a larger production system, we need to have some basic understanding of how long it takes to complete a task posted for completion in a crowdsourcing platform. We present an analysis of the completion time of tasks posted on Amazon Mechanical Turk, based on a dataset containing 165,368 HIT groups, with a total of 6,701,406 HITs, from 9,436 requesters, posted over a period of 15 months.
ABSTRACT In the process of designing recommender systems, textual data are often ignored. In this... more ABSTRACT In the process of designing recommender systems, textual data are often ignored. In this paper we focus on enhancing the quality of recommender systems by considering the textual reviews of items and combining these reviews with numerical ratings. We start by looking at the “Generalized Sentiment Analysis” problem where a multi aspect rating is extracted automatically from a textual review. In an aspect-based review an item is reviewed on many different attributes.
Abstract: The scientific field study of wildlife often requires vigilant observation of detailed ... more Abstract: The scientific field study of wildlife often requires vigilant observation of detailed animal behavior over extended periods. In remote and inhospitable locations, observation can be an arduous, expensive, and dangerous experience for field scientists. We are developing a new class of networked teleoperated robotic “observatories” that allows “citizen scientists” and professional scientists to remotely observe, record, and index animal activity and behaviors via the internet.
Abstract Internet users are increasingly inclined to contribute comments to online news articles,... more Abstract Internet users are increasingly inclined to contribute comments to online news articles, videos, product reviews, and blogs. The most common interface for comments is a list, sorted by time of entry or by binary ratings. It is widely recognized that such lists do not scale well and can lead to" cyberpolarization," which serves to reinforce extreme opinions.
Abstract Standard Sentiment Analysis applies Natural Language Processing methods to assess an" ap... more Abstract Standard Sentiment Analysis applies Natural Language Processing methods to assess an" approval" value of a given text, categorizing it into" negative"," neutral", or" positive" or on a linear scale. Sentiment Analysis can be used to infer ratings values for users based on textual reviews of items such as books, films, or products. We propose an approach to generalizing the concept to multiple dimensions to estimate user ratings along multiple axes such as" service"," price" and" value".
Abstract Many practitioners currently use rules of thumb to price tasks on online labor markets. ... more Abstract Many practitioners currently use rules of thumb to price tasks on online labor markets. Incorrect pricing leads to task starvation or inefficient use of capital. Formal pricing policies can address these challenges. In this paper we argue that a pricing policy can be based on the trade-off between price and desired completion time. We show how this duality can lead to a better pricing policy for tasks in online labor markets. This paper makes three contributions.
ABSTRACT In order to seamlessly integrate a human computation component (eg, Amazon Mechanical Tu... more ABSTRACT In order to seamlessly integrate a human computation component (eg, Amazon Mechanical Turk) within a larger production system, we need to have some basic understanding of how long it takes to complete a task posted for completion in a crowdsourcing platform. We present an analysis of the completion time of tasks posted on Amazon Mechanical Turk, based on a dataset containing 165,368 HIT groups, with a total of 6,701,406 HITs, from 9,436 requesters, posted over a period of 15 months.
ABSTRACT In the process of designing recommender systems, textual data are often ignored. In this... more ABSTRACT In the process of designing recommender systems, textual data are often ignored. In this paper we focus on enhancing the quality of recommender systems by considering the textual reviews of items and combining these reviews with numerical ratings. We start by looking at the “Generalized Sentiment Analysis” problem where a multi aspect rating is extracted automatically from a textual review. In an aspect-based review an item is reviewed on many different attributes.
Abstract: The scientific field study of wildlife often requires vigilant observation of detailed ... more Abstract: The scientific field study of wildlife often requires vigilant observation of detailed animal behavior over extended periods. In remote and inhospitable locations, observation can be an arduous, expensive, and dangerous experience for field scientists. We are developing a new class of networked teleoperated robotic “observatories” that allows “citizen scientists” and professional scientists to remotely observe, record, and index animal activity and behaviors via the internet.
Uploads
Papers by Siamak Faridani