Minimizing information overload: the ranking of electronic messages

Abstract

The decision to examine a message at a particular point in time should be made rationally and economically if the message recipient is to operate efficiently. Electronic message distribution systems, electronic bulletin board systems, and telephone systems capable of leaving digitized voice messages can contribute to "information overload," defined as the economic loss associated with the examination of a number of non-or less-relevant messages. Our model provides a formal method for minimizing expected information overload.The proposed adaptive model predicts the usefulness of a message based on the available message features and may be used to rank messages by expected importance or economic worth. The assumptions of binary and two Poisson independent probabilistic distributions of message feature frequencies are examined, and methods of incorporating these distributions into the ranking model are examined. Ways to incorporate user supplied relevance feedback are suggested. Analytic performance measures are proposed to predict system quality. Other message handling models, including rule based expert systems, are seen as special cases of the model. The performance is given for a set of UNIX shell programs which rank messages. Problems with the use of this formal model are examined, and areas for future research are suggested.

A Generative Model for Statistical Determination of Information Content from Conversation Threads

“…For each thread in the test and training sets, we read the content of the email to determine if it is a broadcast message; if a message is to inform of a decision, a result, news, a meeting time, or anything that doesn't require a reply, we categorize it as a broadcast, otherwise it is considered as a normal message. The ICF of each thread at each f setting is calculated by minimizing (8). A threshold is then chosen to determine if a thread is a broadcast, i.e., a thread is a broadcast if the ICF of the thread is not larger than the threshold, and it is a normal message otherwise.…”

“…The enormous data can easily overwhelm people interested in analyzing the data for social science purposes [2,8]. Needless to say, the data contains valuable information.…”

Not Too Long to Read: The tldr Interface for Exploring and Navigating Large-Scale Discussion Spaces

“…For example, as discussions grow larger, the amount of information that merits attention can exceed the ability of the user's ability to process it [14]. Individuals who attempt to manage more information than they need or want can become overloaded, which in turn leads to inefficiencies for the information system and the user [11]. When confronted with too much information, users tend to resort to the path of least effort [21] and develop strategies to evade being overloaded [8].…”

Browsing document collections: Automatically organizing digital libraries and hypermedia using the gray code

“…Another flaw of this linkless approach is that it assumes statistical feature independence of features. One may wish to assume explicitly that features are statistically dependent, or features that are statistically independent may be developed (Borko, 1985;Deerwester, Dumais, Furnas, Landauer, & Harshman, 1990;Losee, 1989Losee, , 1994. A more elaborate model not making the assumption of statistical feature independence is possible, but more complex.…”